Merge branch 'master' of https://github.com/Itseez/opencv_contrib

modules/README.md

@@ -51,3 +51,5 @@ $ cmake -D OPENCV_EXTRA_MODULES_PATH=<opencv_contrib>/modules -D BUILD_opencv_re
 21. **opencv_xobjdetect**: Integral Channel Features Detector Framework.
 
 22. **opencv_xphoto**: Additional photo processing algorithms: Color balance / Denoising / Inpainting.
+
+23. **opencv_stereo**: Stereo Correspondence done with different descriptors: Census / CS-Census / MCT / BRIEF / MV / RT.

modules/datasets/include/opencv2/datasets/or_pascal.hpp

+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                           License Agreement
+//                For Open Source Computer Vision Library
+//
+// Copyright (C) 2015, Itseez Inc, all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of the copyright holders may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Itseez Inc or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#ifndef OPENCV_DATASETS_VOC_PASCAL_HPP
+#define OPENCV_DATASETS_VOC_PASCAL_HPP
+
+#include <string>
+#include <vector>
+
+#include "opencv2/datasets/dataset.hpp"
+
+#include <opencv2/core.hpp>
+
+namespace cv
+{
+namespace datasets
+{
+
+//! @addtogroup datasets_or
+//! @{
+struct PascalPart: public Object
+{
+    std::string name;
+    int xmin;
+    int ymin;
+    int xmax;
+    int ymax;
+};
+
+struct PascalObj: public PascalPart
+{
+    std::string pose;
+    bool truncated;
+    bool difficult;
+    bool occluded;
+
+    std::vector<PascalPart> parts;
+};
+
+struct OR_pascalObj : public Object
+{
+    std::string filename;
+
+    int width;
+    int height;
+    int depth;
+
+    std::vector<PascalObj> objects;
+};
+
+class CV_EXPORTS OR_pascal : public Dataset
+{
+public:
+    virtual void load(const std::string &path) = 0;
+
+    static Ptr<OR_pascal> create();
+};
+
+//! @}
+
+}// namespace dataset
+}// namespace cv
+
+#endif

modules/datasets/include/opencv2/datasets/pd_inria.hpp

+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                           License Agreement
+//                For Open Source Computer Vision Library
+//
+// Copyright (C) 2015, Itseez Inc, all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of the copyright holders may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Itseez Inc or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#ifndef OPENCV_DATASETS_PD_INRIA_HPP
+#define OPENCV_DATASETS_PD_INRIA_HPP
+
+#include <string>
+#include <vector>
+
+#include "opencv2/datasets/dataset.hpp"
+
+#include <opencv2/core.hpp>
+
+namespace cv
+{
+namespace datasets
+{
+
+//! @addtogroup datasets_pd
+//! @{
+
+enum sampleType 
+{
+    POS = 0,
+    NEG = 1
+};
+
+struct PD_inriaObj : public Object
+{
+    // image file name
+    std::string filename;
+    
+    // positive or negative
+    sampleType sType;
+
+    // image size
+    int width;
+    int height;
+    int depth;
+
+    // bounding boxes
+    std::vector< Rect > bndboxes;
+};
+
+class CV_EXPORTS PD_inria : public Dataset
+{
+public:
+    virtual void load(const std::string &path) = 0;
+
+    static Ptr<PD_inria> create();
+};
+
+//! @}
+
+}
+}
+
+#endif

modules/datasets/samples/or_pascal.cpp

+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                           License Agreement
+//                For Open Source Computer Vision Library
+//
+// Copyright (C) 2015, Itseez Inc, all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of the copyright holders may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Itseez Inc or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#include "opencv2/datasets/or_pascal.hpp"
+
+#include <opencv2/core.hpp>
+
+#include <cstdio>
+#include <cstdlib> // atoi
+
+#include <string>
+#include <vector>
+#include <set>
+
+using namespace std;
+using namespace cv;
+using namespace cv::datasets;
+
+int main(int argc, char *argv[])
+{
+    const char *keys =
+            "{ help h usage ? |    | show this message }"
+            "{ path p         |true| path to folder with dataset }";
+    CommandLineParser parser(argc, argv, keys);
+    string path(parser.get<string>("path"));
+    if (parser.has("help") || path=="true")
+    {
+        parser.printMessage();
+        return -1;
+    }
+
+    Ptr<OR_pascal> dataset = OR_pascal::create();
+    dataset->load(path);
+
+    // Print train/test/validation size and first example
+    OR_pascalObj *example;
+    vector< Ptr<Object> > &train = dataset->getTrain();
+    printf("\ntrain:\nsize: %u", (unsigned int)train.size());
+    example = static_cast<OR_pascalObj *>(train[0].get());
+    printf("\nfirst image: \n%s", example->filename.c_str());
+
+    printf("\nsize:");
+    printf("\n - width: %d", example->width);
+    printf("\n - height: %d", example->height);
+    printf("\n - depth: %d", example->depth);
+
+    for (unsigned int i = 0; i < example->objects.size(); i++)
+    {
+        printf("\nobject %d", i);
+        printf("\nname: %s", example->objects[i].name.c_str());
+        printf("\npose: %s", example->objects[i].pose.c_str());
+        printf("\ntruncated: %d", example->objects[i].truncated);
+        printf("\ndifficult: %d", example->objects[i].difficult);
+        printf("\noccluded: %d", example->objects[i].occluded);
+
+        printf("\nbounding box:");
+        printf("\n - xmin: %d", example->objects[i].xmin);
+        printf("\n - ymin: %d", example->objects[i].ymin);
+        printf("\n - xmax: %d", example->objects[i].xmax);
+        printf("\n - ymax: %d", example->objects[i].ymax);
+    }
+
+    vector< Ptr<Object> > &test = dataset->getTest();
+    printf("\ntest:\nsize: %u", (unsigned int)test.size());
+    example = static_cast<OR_pascalObj *>(test[0].get());
+    printf("\nfirst image: \n%s", example->filename.c_str());
+
+    vector< Ptr<Object> > &validation = dataset->getValidation();
+    printf("\nvalidation:\nsize: %u", (unsigned int)validation.size());
+    example = static_cast<OR_pascalObj *>(validation[0].get());
+    printf("\nfirst image: \n%s\n", example->filename.c_str());
+
+    return 0;
+}

modules/datasets/samples/pd_inria.cpp

+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                           License Agreement
+//                For Open Source Computer Vision Library
+//
+// Copyright (C) 2015, Itseez Inc, all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of the copyright holders may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Itseez Inc or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#include "opencv2/datasets/pd_inria.hpp"
+#include <opencv2/core.hpp>
+
+#include <iostream>
+#include <string>
+#include <vector>
+
+using namespace std;
+using namespace cv;
+using namespace cv::datasets;
+
+int main(int argc, char *argv[])
+{
+    const char *keys =
+            "{ help h usage ? |    | show this message }"
+            "{ path p         |true| path to dataset }";
+    CommandLineParser parser(argc, argv, keys);
+    string path(parser.get<string>("path"));
+    if (parser.has("help") || path=="true")
+    {
+        parser.printMessage();
+        return -1;
+    }
+
+    Ptr<PD_inria> dataset = PD_inria::create();
+    dataset->load(path);
+
+    cout << "train size: " << (unsigned int)dataset->getTrain().size() << endl;
+
+    PD_inriaObj *example = static_cast<PD_inriaObj *>(dataset->getTrain()[0].get());
+    cout << "first train object: " << endl;
+    cout << "name: " << example->filename << endl;
+    
+    // image size
+    cout << "image size: " << endl;
+    cout << "  - width: " << example->width << endl;
+    cout << "  - height: " << example->height << endl;
+    cout << "  - depth: " << example->depth << endl;
+
+    // bounding boxes
+    for (unsigned int i = 0; i < (example->bndboxes).size(); i++)
+    {
+        cout << "object " << i << endl;
+        int x = (example->bndboxes)[i].x;
+        int y = (example->bndboxes)[i].y;
+        cout << "  - xmin = " << x  << endl;
+        cout << "  - ymin = " << y << endl;
+        cout << "  - xmax = " << (example->bndboxes)[i].width + x << endl;
+        cout << "  - ymax = " << (example->bndboxes)[i].height + y<< endl;
+    }
+
+    return 0;
+}

modules/datasets/src/or_pascal.cpp

+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                           License Agreement
+//                For Open Source Computer Vision Library
+//
+// Copyright (C) 2015, Itseez Inc, all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of the copyright holders may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Itseez Inc or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#include "opencv2/datasets/or_pascal.hpp"
+#include "opencv2/datasets/util.hpp"
+#include <opencv2/datasets/tinyxml2/tinyxml2.h>
+#include <fstream>
+
+namespace cv
+{
+namespace datasets
+{
+
+using namespace std;
+using namespace tinyxml2;
+
+class OR_pascalImp : public OR_pascal
+{
+public:
+    OR_pascalImp() {}
+
+    virtual void load(const string &path);
+
+private:
+    void loadDataset(const string &path, const string &nameImageSet, vector< Ptr<Object> > &imageSet);
+    Ptr<Object> parseAnnotation(const string path, const string id);
+    const char*  parseNodeText(XMLElement* node, const string nodeName, const string defaultValue);
+};
+
+
+void OR_pascalImp::load(const string &path)
+{
+    train.push_back(vector< Ptr<Object> >());
+    test.push_back(vector< Ptr<Object> >());
+    validation.push_back(vector< Ptr<Object> >());
+
+    loadDataset(path, "train", train.back());
+    loadDataset(path, "test", test.back());
+    loadDataset(path, "val", validation.back());
+}
+
+void OR_pascalImp::loadDataset(const string &path, const string &nameImageSet, vector< Ptr<Object> > &imageSet)
+{
+    string pathImageSets(path + "ImageSets/Main/");
+    string imageList = pathImageSets + nameImageSet + ".txt";
+
+    ifstream in(imageList.c_str());
+    string error_message = format("Image list not exists!\n%s", imageList.c_str());
+
+    if (!in.is_open())
+        CV_Error(Error::StsBadArg, error_message);
+
+    string id = "";
+
+    while( getline(in, id) )
+    {
+        if( strcmp(nameImageSet.c_str(), "test") == 0 ) // test set ground truth is not available
+        {
+            Ptr<OR_pascalObj> annotation(new OR_pascalObj);
+            annotation->filename = path + "JPEGImages/" + id + ".jpg";
+            imageSet.push_back(annotation);
+        }
+        else
+        {
+            imageSet.push_back(parseAnnotation(path, id));
+        }
+    }
+}
+
+const char* OR_pascalImp::parseNodeText(XMLElement* node, const string nodeName, const string defaultValue)
+{
+    const char* e = node->FirstChildElement(nodeName.c_str())->GetText();
+
+    if( e != 0 )
+        return e ;
+    else
+        return defaultValue.c_str();
+}
+
+Ptr<Object> OR_pascalImp::parseAnnotation(const string path, const string id)
+{
+    string pathAnnotations(path + "Annotations/");
+    string pathImages(path + "JPEGImages/");
+    Ptr<OR_pascalObj> annotation(new OR_pascalObj);
+
+    XMLDocument doc;
+    string xml_file = pathAnnotations + id + ".xml";
+
+    XMLError error_code = doc.LoadFile(xml_file.c_str());
+    string error_message = format("Parsing XML failed. Error code = %d. \nFile = %s", error_code, xml_file.c_str());
+    switch (error_code)
+    {
+        case XML_SUCCESS:
+            break;
+        case XML_ERROR_FILE_NOT_FOUND:
+            error_message = "XML file not found! " + error_message;
+            CV_Error(Error::StsParseError, error_message);
+            return annotation;
+        default:
+            CV_Error(Error::StsParseError, error_message);
+            break;
+    }
+
+    // <annotation/>
+    XMLElement *xml_ann = doc.RootElement();
+
+    // <filename/>
+    string img_name = xml_ann->FirstChildElement("filename")->GetText();
+    annotation->filename = pathImages + img_name;
+
+    // <size/>
+    XMLElement *sz = xml_ann->FirstChildElement("size");
+    int width = atoi(sz->FirstChildElement("width")->GetText());
+    int height = atoi(sz->FirstChildElement("height")->GetText());
+    int depth = atoi(sz->FirstChildElement("depth")->GetText());
+    annotation->width = width;
+    annotation->height = height;
+    annotation->depth = depth;
+
+    // <object/>
+    vector<PascalObj> objects;
+    XMLElement *xml_obj = xml_ann->FirstChildElement("object");
+
+    while (xml_obj)
+    {
+        PascalObj pascal_obj;
+        pascal_obj.name = xml_obj->FirstChildElement("name")->GetText();
+        pascal_obj.pose = parseNodeText(xml_obj, "pose", "Unspecified");
+        pascal_obj.truncated = atoi(parseNodeText(xml_obj, "truncated", "0")) > 0;
+        pascal_obj.difficult = atoi(parseNodeText(xml_obj, "difficult", "0")) > 0;
+        pascal_obj.occluded = atoi(parseNodeText(xml_obj, "occluded", "0")) > 0;
+
+        // <bndbox/>
+        XMLElement *xml_bndbox = xml_obj->FirstChildElement("bndbox");
+        pascal_obj.xmin = atoi(xml_bndbox->FirstChildElement("xmin")->GetText());
+        pascal_obj.ymin = atoi(xml_bndbox->FirstChildElement("ymin")->GetText());
+        pascal_obj.xmax = atoi(xml_bndbox->FirstChildElement("xmax")->GetText());
+        pascal_obj.ymax = atoi(xml_bndbox->FirstChildElement("ymax")->GetText());
+
+        // <part/>
+        vector<PascalPart> parts;
+        XMLElement *xml_part = xml_obj->FirstChildElement("part");
+
+        while (xml_part)
+        {
+            PascalPart pascal_part;
+            pascal_part.name = xml_part->FirstChildElement("name")->GetText();
+
+            xml_bndbox = xml_part->FirstChildElement("bndbox");
+            pascal_part.xmin = atoi(xml_bndbox->FirstChildElement("xmin")->GetText());
+            pascal_part.ymin = atoi(xml_bndbox->FirstChildElement("ymin")->GetText());
+            pascal_part.xmax = atoi(xml_bndbox->FirstChildElement("xmax")->GetText());
+            pascal_part.ymax = atoi(xml_bndbox->FirstChildElement("ymax")->GetText());
+            parts.push_back(pascal_part);
+
+            xml_part = xml_part->NextSiblingElement("part");
+        }
+
+        pascal_obj.parts = parts;
+        objects.push_back(pascal_obj);
+
+        xml_obj = xml_obj->NextSiblingElement("object");
+    }
+
+    annotation->objects = objects;
+
+    return annotation;
+}
+
+Ptr<OR_pascal> OR_pascal::create()
+{
+    return Ptr<OR_pascalImp>(new OR_pascalImp);
+}
+
+}
+}

modules/datasets/src/pd_inria.cpp

+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                           License Agreement
+//                For Open Source Computer Vision Library
+//
+// Copyright (C) 2015, Itseez Inc, all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of the copyright holders may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Itseez Inc or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#include "opencv2/datasets/pd_inria.hpp"
+#include "opencv2/datasets/util.hpp"
+
+namespace cv
+{
+namespace datasets
+{
+
+using namespace std;
+
+class PD_inriaImp : public PD_inria
+{
+public:
+    PD_inriaImp() {}
+    
+    virtual ~PD_inriaImp() {}
+
+    virtual void load(const string &path);
+
+private:
+    void loadDataset(const string &path, const string nameImageSet, vector< Ptr<Object> > &imageSet);
+    void readTextLines(const string filename, vector< string > &lines);
+    void parseAnnotation(const string filename, Ptr< PD_inriaObj > &object);
+};
+
+void PD_inriaImp::load(const string &path)
+{
+    // Training set
+    train.push_back(vector< Ptr<Object> >());
+    loadDataset(path, "Train", train.back());
+    
+    // Testing set
+    test.push_back(vector< Ptr<Object> >());
+    loadDataset(path, "Test", test.back());
+
+    // There is no validation set
+    validation.push_back(vector< Ptr<Object> >());
+}
+
+void PD_inriaImp::readTextLines(const string filename, vector< string > &lines)
+{
+    ifstream in(filename.c_str());
+    string error_message = "";
+
+    if (!in.is_open())
+    {
+        error_message = format("Unable to open file: \n%s\n", filename.c_str());
+        CV_Error(Error::StsBadArg, error_message);
+    }
+
+    string currline = "";
+
+    while (getline(in, currline))
+        lines.push_back(currline);
+}
+
+void PD_inriaImp::parseAnnotation(const string filename, Ptr< PD_inriaObj > &object)
+{
+    string error_message = "";
+
+    ifstream in(filename.c_str());
+
+    if (!in.is_open())
+    {
+        error_message = format("Unable to open file: \n%s\n", filename.c_str());
+        CV_Error(Error::StsBadArg, error_message);
+    }
+    
+    string imageSizeHeader = "Image size (X x Y x C) : ";
+    string imageSizeFmt = imageSizeHeader + "%d x %d x %d";
+    string objWithGTHeader = "Objects with ground truth : ";
+    string objWithGTFmt = objWithGTHeader + "%d { \"PASperson\" }";
+    string boundBoxHeader = "Bounding box for object ";
+    string boundBoxFmt = boundBoxHeader + "%*d \"PASperson\" (Xmin, Ymin) - (Xmax, Ymax) : (%d, %d) - (%d, %d)";
+    
+    string line = "";
+    
+    int width = 0;
+    int height = 0;
+    int depth = 0;
+    int xmin, ymin, xmax, ymax;
+
+    int numObjects = 0;
+
+    while (getline(in, line))
+    {
+        if (line[0] == '#' || !line[0])
+            continue;
+
+        if (strstr(line.c_str(), imageSizeHeader.c_str()))
+        {
+            sscanf(line.c_str(), imageSizeFmt.c_str(), &width, &height, &depth);
+            object->width = width;
+            object->height = height;
+            object->depth = depth;
+        }
+        else if (strstr(line.c_str(), objWithGTHeader.c_str()))
+        {
+            sscanf(line.c_str(), objWithGTFmt.c_str(), &numObjects);
+            
+            if (numObjects <= 0)
+                break;
+        }
+        else if (strstr(line.c_str(), boundBoxHeader.c_str()))
+        {
+            sscanf(line.c_str(), boundBoxFmt.c_str(), &xmin, &ymin, &xmax, &ymax);
+            Rect bndbox;
+            bndbox.x = xmin;
+            bndbox.y = ymin;
+            bndbox.width = xmax - xmin;
+            bndbox.height = ymax - ymin;
+            (object->bndboxes).push_back(bndbox);
+        }
+    }
+
+    CV_Assert((object->bndboxes).size() == (unsigned int)numObjects);
+}
+
+void PD_inriaImp::loadDataset(const string &path, const string nameImageSet, vector< Ptr<Object> > &imageSet)
+{
+    string listAnn = path + nameImageSet + "/annotations.lst";
+    string listPos = path + nameImageSet + "/pos.lst";
+    string listNeg = path + nameImageSet + "/neg.lst";
+    
+    vector< string > fsAnn;
+    vector< string > fsPos;
+    vector< string > fsNeg;
+   
+    // read file names
+    readTextLines(listAnn, fsAnn);
+    readTextLines(listPos, fsPos);
+    readTextLines(listNeg, fsNeg);
+   
+    CV_Assert(fsAnn.size() == fsPos.size());
+
+    for (unsigned int i = 0; i < fsPos.size(); i++)
+    {
+        Ptr<PD_inriaObj> curr(new PD_inriaObj);
+        parseAnnotation(path + fsAnn[i], curr);
+        curr->filename = path + fsPos[i];
+        curr->sType = POS;
+        
+        imageSet.push_back(curr);
+    }
+    
+    for (unsigned int i = 0; i < fsNeg.size(); i++)
+    {
+        Ptr<PD_inriaObj> curr(new PD_inriaObj);
+        curr->filename = path + fsNeg[i]; 
+        curr->sType = NEG;
+        
+        imageSet.push_back(curr);
+    }
+}
+
+Ptr<PD_inria> PD_inria::create()
+{
+    return Ptr<PD_inriaImp>(new PD_inriaImp);
+}
+
+}
+}

modules/face/CMakeLists.txt

 set(the_description "Face recognition etc")
-ocv_define_module(face opencv_core opencv_imgproc WRAP python)
+ocv_define_module(face opencv_core opencv_imgproc opencv_objdetect WRAP python)
+# NOTE: objdetect module is needed for one of the samples

modules/face/doc/src/facerec_demo.cpp

-/*
- * Copyright (c) 2011. Philipp Wagner <bytefish[at]gmx[dot]de>.
- * Released to public domain under terms of the BSD Simplified license.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in the
- *     documentation and/or other materials provided with the distribution.
- *   * Neither the name of the organization nor the names of its contributors
- *     may be used to endorse or promote products derived from this software
- *     without specific prior written permission.
- *
- *   See <http://www.opensource.org/licenses/bsd-license>
- */
-
-#include "opencv2/core.hpp"
-#include "opencv2/face.hpp"
-#include "opencv2/highgui.hpp"
-
-#include <iostream>
-#include <fstream>
-#include <sstream>
-
-using namespace cv;
-using namespace cv::face;
-using namespace std;
-
-static Mat norm_0_255(InputArray _src) {
-    Mat src = _src.getMat();
-    // Create and return normalized image:
-    Mat dst;
-    switch(src.channels()) {
-    case 1:
-        cv::normalize(_src, dst, 0, 255, NORM_MINMAX, CV_8UC1);
-        break;
-    case 3:
-        cv::normalize(_src, dst, 0, 255, NORM_MINMAX, CV_8UC3);
-        break;
-    default:
-        src.copyTo(dst);
-        break;
-    }
-    return dst;
-}
-
-static void read_csv(const string& filename, vector<Mat>& images, vector<int>& labels, char separator = ';') {
-    std::ifstream file(filename.c_str(), ifstream::in);
-    if (!file) {
-        string error_message = "No valid input file was given, please check the given filename.";
-        CV_Error(CV_StsBadArg, error_message);
-    }
-    string line, path, classlabel;
-    while (getline(file, line)) {
-        stringstream liness(line);
-        getline(liness, path, separator);
-        getline(liness, classlabel);
-        if(!path.empty() && !classlabel.empty()) {
-            images.push_back(imread(path, 0));
-            labels.push_back(atoi(classlabel.c_str()));
-        }
-    }
-}
-
-int main(int argc, const char *argv[]) {
-    // Check for valid command line arguments, print usage
-    // if no arguments were given.
-    if (argc != 2) {
-        cout << "usage: " << argv[0] << " <csv.ext>" << endl;
-        exit(1);
-    }
-    // Get the path to your CSV.
-    string fn_csv = string(argv[1]);
-    // These vectors hold the images and corresponding labels.
-    vector<Mat> images;
-    vector<int> labels;
-    // Read in the data. This can fail if no valid
-    // input filename is given.
-    try {
-        read_csv(fn_csv, images, labels);
-    } catch (cv::Exception& e) {
-        cerr << "Error opening file \"" << fn_csv << "\". Reason: " << e.msg << endl;
-        // nothing more we can do
-        exit(1);
-    }
-    // Quit if there are not enough images for this demo.
-    if(images.size() <= 1) {
-        string error_message = "This demo needs at least 2 images to work. Please add more images to your data set!";
-        CV_Error(CV_StsError, error_message);
-    }
-    // Get the height from the first image. We'll need this
-    // later in code to reshape the images to their original
-    // size:
-    int height = images[0].rows;
-    // The following lines simply get the last images from
-    // your dataset and remove it from the vector. This is
-    // done, so that the training data (which we learn the
-    // cv::FaceRecognizer on) and the test data we test
-    // the model with, do not overlap.
-    Mat testSample = images[images.size() - 1];
-    int testLabel = labels[labels.size() - 1];
-    images.pop_back();
-    labels.pop_back();
-    // The following lines create an Eigenfaces model for
-    // face recognition and train it with the images and
-    // labels read from the given CSV file.
-    // This here is a full PCA, if you just want to keep
-    // 10 principal components (read Eigenfaces), then call
-    // the factory method like this:
-    //
-    //      cv::createEigenFaceRecognizer(10);
-    //
-    // If you want to create a FaceRecognizer with a
-    // confidennce threshold, call it with:
-    //
-    //      cv::createEigenFaceRecognizer(10, 123.0);
-    //
-    Ptr<FaceRecognizer> model = createFisherFaceRecognizer();
-    model->train(images, labels);
-    // The following line predicts the label of a given
-    // test image:
-    int predictedLabel = model->predict(testSample);
-    //
-    // To get the confidence of a prediction call the model with:
-    //
-    //      int predictedLabel = -1;
-    //      double confidence = 0.0;
-    //      model->predict(testSample, predictedLabel, confidence);
-    //
-    string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
-    cout << result_message << endl;
-    // Sometimes you'll need to get/set internal model data,
-    // which isn't exposed by the public cv::FaceRecognizer.
-    // Since each cv::FaceRecognizer is derived from a
-    // cv::Algorithm, you can query the data.
-    //
-    // First we'll use it to set the threshold of the FaceRecognizer
-    // to 0.0 without retraining the model. This can be useful if
-    // you are evaluating the model:
-    //
-    model->set("threshold", 0.0);
-    // Now the threshold of this model is set to 0.0. A prediction
-    // now returns -1, as it's impossible to have a distance below
-    // it
-    predictedLabel = model->predict(testSample);
-    cout << "Predicted class = " << predictedLabel << endl;
-    // Here is how to get the eigenvalues of this Eigenfaces model:
-    Mat eigenvalues = model->getMat("eigenvalues");
-    // And we can do the same to display the Eigenvectors (read Eigenfaces):
-    Mat W = model->getMat("eigenvectors");
-    // From this we will display the (at most) first 10 Eigenfaces:
-    for (int i = 0; i < min(10, W.cols); i++) {
-        string msg = format("Eigenvalue #%d = %.5f", i, eigenvalues.at<double>(i));
-        cout << msg << endl;
-        // get eigenvector #i
-        Mat ev = W.col(i).clone();
-        // Reshape to original size & normalize to [0...255] for imshow.
-        Mat grayscale = norm_0_255(ev.reshape(1, height));
-        // Show the image & apply a Jet colormap for better sensing.
-        Mat cgrayscale;
-        applyColorMap(grayscale, cgrayscale, COLORMAP_JET);
-        imshow(format("%d", i), cgrayscale);
-    }
-    waitKey(0);
-
-    return 0;
-}

modules/face/samples/src/facerec_eigenfaces.cpp → modules/face/samples/facerec_eigenfaces.cpp

@@ -19,6 +19,7 @@
 #include "opencv2/core.hpp"
 #include "opencv2/face.hpp"
 #include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
 
 #include <iostream>
 #include <fstream>
@@ -50,7 +51,7 @@ static void read_csv(const string& filename, vector<Mat>& images, vector<int>& l
     std::ifstream file(filename.c_str(), ifstream::in);
     if (!file) {
         string error_message = "No valid input file was given, please check the given filename.";
-        CV_Error(CV_StsBadArg, error_message);
+        CV_Error(Error::StsBadArg, error_message);
     }
     string line, path, classlabel;
     while (getline(file, line)) {
@@ -92,7 +93,7 @@ int main(int argc, const char *argv[]) {
     // Quit if there are not enough images for this demo.
     if(images.size() <= 1) {
         string error_message = "This demo needs at least 2 images to work. Please add more images to your data set!";
-        CV_Error(CV_StsError, error_message);
+        CV_Error(Error::StsError, error_message);
     }
     // Get the height from the first image. We'll need this
     // later in code to reshape the images to their original
@@ -101,7 +102,7 @@ int main(int argc, const char *argv[]) {
     // The following lines simply get the last images from
     // your dataset and remove it from the vector. This is
     // done, so that the training data (which we learn the
-    // cv::FaceRecognizer on) and the test data we test
+    // cv::BasicFaceRecognizer on) and the test data we test
     // the model with, do not overlap.
     Mat testSample = images[images.size() - 1];
     int testLabel = labels[labels.size() - 1];
@@ -126,7 +127,7 @@ int main(int argc, const char *argv[]) {
     //
     //      cv::createEigenFaceRecognizer(0, 123.0);
     //
-    Ptr<FaceRecognizer> model = createEigenFaceRecognizer();
+    Ptr<BasicFaceRecognizer> model = createEigenFaceRecognizer();
     model->train(images, labels);
     // The following line predicts the label of a given
     // test image:
@@ -141,11 +142,11 @@ int main(int argc, const char *argv[]) {
     string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
     cout << result_message << endl;
     // Here is how to get the eigenvalues of this Eigenfaces model:
-    Mat eigenvalues = model->getMat("eigenvalues");
+    Mat eigenvalues = model->getEigenValues();
     // And we can do the same to display the Eigenvectors (read Eigenfaces):
-    Mat W = model->getMat("eigenvectors");
+    Mat W = model->getEigenVectors();
     // Get the sample mean from the training data
-    Mat mean = model->getMat("mean");
+    Mat mean = model->getMean();
     // Display or save:
     if(argc == 2) {
         imshow("mean", norm_0_255(mean.reshape(1, images[0].rows)));
@@ -175,8 +176,8 @@ int main(int argc, const char *argv[]) {
     for(int num_components = min(W.cols, 10); num_components < min(W.cols, 300); num_components+=15) {
         // slice the eigenvectors from the model
         Mat evs = Mat(W, Range::all(), Range(0, num_components));
-        Mat projection = subspaceProject(evs, mean, images[0].reshape(1,1));
-        Mat reconstruction = subspaceReconstruct(evs, mean, projection);
+        Mat projection = LDA::subspaceProject(evs, mean, images[0].reshape(1,1));
+        Mat reconstruction = LDA::subspaceReconstruct(evs, mean, projection);
         // Normalize the result:
         reconstruction = norm_0_255(reconstruction.reshape(1, images[0].rows));
         // Display or save:

modules/face/samples/src/facerec_fisherfaces.cpp → modules/face/samples/facerec_fisherfaces.cpp

@@ -19,6 +19,7 @@
 #include "opencv2/core.hpp"
 #include "opencv2/face.hpp"
 #include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
 
 #include <iostream>
 #include <fstream>
@@ -50,7 +51,7 @@ static void read_csv(const string& filename, vector<Mat>& images, vector<int>& l
     std::ifstream file(filename.c_str(), ifstream::in);
     if (!file) {
         string error_message = "No valid input file was given, please check the given filename.";
-        CV_Error(CV_StsBadArg, error_message);
+        CV_Error(Error::StsBadArg, error_message);
     }
     string line, path, classlabel;
     while (getline(file, line)) {
@@ -92,7 +93,7 @@ int main(int argc, const char *argv[]) {
     // Quit if there are not enough images for this demo.
     if(images.size() <= 1) {
         string error_message = "This demo needs at least 2 images to work. Please add more images to your data set!";
-        CV_Error(CV_StsError, error_message);
+        CV_Error(Error::StsError, error_message);
     }
     // Get the height from the first image. We'll need this
     // later in code to reshape the images to their original
@@ -101,7 +102,7 @@ int main(int argc, const char *argv[]) {
     // The following lines simply get the last images from
     // your dataset and remove it from the vector. This is
     // done, so that the training data (which we learn the
-    // cv::FaceRecognizer on) and the test data we test
+    // cv::BasicFaceRecognizer on) and the test data we test
     // the model with, do not overlap.
     Mat testSample = images[images.size() - 1];
     int testLabel = labels[labels.size() - 1];
@@ -125,7 +126,7 @@ int main(int argc, const char *argv[]) {
     //
     //      cv::createFisherFaceRecognizer(0, 123.0);
     //
-    Ptr<FaceRecognizer> model = createFisherFaceRecognizer();
+    Ptr<BasicFaceRecognizer> model = createFisherFaceRecognizer();
     model->train(images, labels);
     // The following line predicts the label of a given
     // test image:
@@ -140,11 +141,11 @@ int main(int argc, const char *argv[]) {
     string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
     cout << result_message << endl;
     // Here is how to get the eigenvalues of this Eigenfaces model:
-    Mat eigenvalues = model->getMat("eigenvalues");
+    Mat eigenvalues = model->getEigenValues();
     // And we can do the same to display the Eigenvectors (read Eigenfaces):
-    Mat W = model->getMat("eigenvectors");
+    Mat W = model->getEigenVectors();
     // Get the sample mean from the training data
-    Mat mean = model->getMat("mean");
+    Mat mean = model->getMean();
     // Display or save:
     if(argc == 2) {
         imshow("mean", norm_0_255(mean.reshape(1, images[0].rows)));
@@ -173,8 +174,8 @@ int main(int argc, const char *argv[]) {
     for(int num_component = 0; num_component < min(16, W.cols); num_component++) {
         // Slice the Fisherface from the model:
         Mat ev = W.col(num_component);
-        Mat projection = subspaceProject(ev, mean, images[0].reshape(1,1));
-        Mat reconstruction = subspaceReconstruct(ev, mean, projection);
+        Mat projection = LDA::subspaceProject(ev, mean, images[0].reshape(1,1));
+        Mat reconstruction = LDA::subspaceReconstruct(ev, mean, projection);
         // Normalize the result:
         reconstruction = norm_0_255(reconstruction.reshape(1, images[0].rows));
         // Display or save:

modules/face/samples/src/facerec_lbph.cpp → modules/face/samples/facerec_lbph.cpp

@@ -32,7 +32,7 @@ static void read_csv(const string& filename, vector<Mat>& images, vector<int>& l
     std::ifstream file(filename.c_str(), ifstream::in);
     if (!file) {
         string error_message = "No valid input file was given, please check the given filename.";
-        CV_Error(CV_StsBadArg, error_message);
+        CV_Error(Error::StsBadArg, error_message);
     }
     string line, path, classlabel;
     while (getline(file, line)) {
@@ -70,16 +70,12 @@ int main(int argc, const char *argv[]) {
     // Quit if there are not enough images for this demo.
     if(images.size() <= 1) {
         string error_message = "This demo needs at least 2 images to work. Please add more images to your data set!";
-        CV_Error(CV_StsError, error_message);
+        CV_Error(Error::StsError, error_message);
     }
-    // Get the height from the first image. We'll need this
-    // later in code to reshape the images to their original
-    // size:
-    int height = images[0].rows;
     // The following lines simply get the last images from
     // your dataset and remove it from the vector. This is
     // done, so that the training data (which we learn the
-    // cv::FaceRecognizer on) and the test data we test
+    // cv::LBPHFaceRecognizer on) and the test data we test
     // the model with, do not overlap.
     Mat testSample = images[images.size() - 1];
     int testLabel = labels[labels.size() - 1];
@@ -107,7 +103,7 @@ int main(int argc, const char *argv[]) {
     //
     //      cv::createLBPHFaceRecognizer(1,8,8,8,123.0)
     //
-    Ptr<FaceRecognizer> model = createLBPHFaceRecognizer();
+    Ptr<LBPHFaceRecognizer> model = createLBPHFaceRecognizer();
     model->train(images, labels);
     // The following line predicts the label of a given
     // test image:
@@ -121,16 +117,11 @@ int main(int argc, const char *argv[]) {
     //
     string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
     cout << result_message << endl;
-    // Sometimes you'll need to get/set internal model data,
-    // which isn't exposed by the public cv::FaceRecognizer.
-    // Since each cv::FaceRecognizer is derived from a
-    // cv::Algorithm, you can query the data.
-    //
-    // First we'll use it to set the threshold of the FaceRecognizer
+    // First we'll use it to set the threshold of the LBPHFaceRecognizer
     // to 0.0 without retraining the model. This can be useful if
     // you are evaluating the model:
     //
-    model->set("threshold", 0.0);
+    model->setThreshold(0.0);
     // Now the threshold of this model is set to 0.0. A prediction
     // now returns -1, as it's impossible to have a distance below
     // it
@@ -142,14 +133,14 @@ int main(int argc, const char *argv[]) {
     // within the model:
     cout << "Model Information:" << endl;
     string model_info = format("\tLBPH(radius=%i, neighbors=%i, grid_x=%i, grid_y=%i, threshold=%.2f)",
-            model->getInt("radius"),
-            model->getInt("neighbors"),
-            model->getInt("grid_x"),
-            model->getInt("grid_y"),
-            model->getDouble("threshold"));
+            model->getRadius(),
+            model->getNeighbors(),
+            model->getGridX(),
+            model->getGridY(),
+            model->getThreshold());
     cout << model_info << endl;
     // We could get the histograms for example:
-    vector<Mat> histograms = model->getMatVector("histograms");
+    vector<Mat> histograms = model->getHistograms();
     // But should I really visualize it? Probably the length is interesting:
     cout << "Size of the histograms: " << histograms[0].total() << endl;
     return 0;

modules/face/samples/src/facerec_save_load.cpp → modules/face/samples/facerec_save_load.cpp

@@ -19,6 +19,7 @@
 #include "opencv2/core.hpp"
 #include "opencv2/face.hpp"
 #include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
 
 #include <iostream>
 #include <fstream>
@@ -50,7 +51,7 @@ static void read_csv(const string& filename, vector<Mat>& images, vector<int>& l
     std::ifstream file(filename.c_str(), ifstream::in);
     if (!file) {
         string error_message = "No valid input file was given, please check the given filename.";
-        CV_Error(CV_StsBadArg, error_message);
+        CV_Error(Error::StsBadArg, error_message);
     }
     string line, path, classlabel;
     while (getline(file, line)) {
@@ -92,7 +93,7 @@ int main(int argc, const char *argv[]) {
     // Quit if there are not enough images for this demo.
     if(images.size() <= 1) {
         string error_message = "This demo needs at least 2 images to work. Please add more images to your data set!";
-        CV_Error(CV_StsError, error_message);
+        CV_Error(Error::StsError, error_message);
     }
     // Get the height from the first image. We'll need this
     // later in code to reshape the images to their original
@@ -126,7 +127,7 @@ int main(int argc, const char *argv[]) {
     //
     //      cv::createEigenFaceRecognizer(0, 123.0);
     //
-    Ptr<FaceRecognizer> model0 = createEigenFaceRecognizer();
+    Ptr<BasicFaceRecognizer> model0 = createEigenFaceRecognizer();
     model0->train(images, labels);
     // save the model to eigenfaces_at.yaml
     model0->save("eigenfaces_at.yml");
@@ -134,7 +135,7 @@ int main(int argc, const char *argv[]) {
     //
     // Now create a new Eigenfaces Recognizer
     //
-    Ptr<FaceRecognizer> model1 = createEigenFaceRecognizer();
+    Ptr<BasicFaceRecognizer> model1 = createEigenFaceRecognizer();
     model1->load("eigenfaces_at.yml");
     // The following line predicts the label of a given
     // test image:
@@ -149,11 +150,11 @@ int main(int argc, const char *argv[]) {
     string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
     cout << result_message << endl;
     // Here is how to get the eigenvalues of this Eigenfaces model:
-    Mat eigenvalues = model1->getMat("eigenvalues");
+    Mat eigenvalues = model1->getEigenValues();
     // And we can do the same to display the Eigenvectors (read Eigenfaces):
-    Mat W = model1->getMat("eigenvectors");
+    Mat W = model1->getEigenVectors();
     // Get the sample mean from the training data
-    Mat mean = model1->getMat("mean");
+    Mat mean = model1->getMean();
     // Display or save:
     if(argc == 2) {
         imshow("mean", norm_0_255(mean.reshape(1, images[0].rows)));
@@ -182,8 +183,8 @@ int main(int argc, const char *argv[]) {
     for(int num_components = 10; num_components < 300; num_components+=15) {
         // slice the eigenvectors from the model
         Mat evs = Mat(W, Range::all(), Range(0, num_components));
-        Mat projection = subspaceProject(evs, mean, images[0].reshape(1,1));
-        Mat reconstruction = subspaceReconstruct(evs, mean, projection);
+        Mat projection = LDA::subspaceProject(evs, mean, images[0].reshape(1,1));
+        Mat reconstruction = LDA::subspaceReconstruct(evs, mean, projection);
         // Normalize the result:
         reconstruction = norm_0_255(reconstruction.reshape(1, images[0].rows));
         // Display or save:

modules/face/samples/src/facerec_video.cpp → modules/face/samples/facerec_video.cpp

@@ -34,7 +34,7 @@ static void read_csv(const string& filename, vector<Mat>& images, vector<int>& l
     std::ifstream file(filename.c_str(), ifstream::in);
     if (!file) {
         string error_message = "No valid input file was given, please check the given filename.";
-        CV_Error(CV_StsBadArg, error_message);
+        CV_Error(Error::StsBadArg, error_message);
     }
     string line, path, classlabel;
     while (getline(file, line)) {
@@ -79,7 +79,7 @@ int main(int argc, const char *argv[]) {
     int im_width = images[0].cols;
     int im_height = images[0].rows;
     // Create a FaceRecognizer and train it on the given images:
-    Ptr<FaceRecognizer> model = createFisherFaceRecognizer();
+    Ptr<BasicFaceRecognizer> model = createFisherFaceRecognizer();
     model->train(images, labels);
     // That's it for learning the Face Recognition model. You now
     // need to create the classifier for the task of Face Detection.
@@ -103,14 +103,14 @@ int main(int argc, const char *argv[]) {
         Mat original = frame.clone();
         // Convert the current frame to grayscale:
         Mat gray;
-        cvtColor(original, gray, CV_BGR2GRAY);
+        cvtColor(original, gray, COLOR_BGR2GRAY);
         // Find the faces in the frame:
         vector< Rect_<int> > faces;
         haar_cascade.detectMultiScale(gray, faces);
         // At this point you have the position of the faces in
         // faces. Now we'll get the faces, make a prediction and
         // annotate it in the video. Cool or what?
-        for(int i = 0; i < faces.size(); i++) {
+        for(size_t i = 0; i < faces.size(); i++) {
             // Process face by face:
             Rect face_i = faces[i];
             // Crop the face from the image. So simple with OpenCV C++:
@@ -131,7 +131,7 @@ int main(int argc, const char *argv[]) {
             int prediction = model->predict(face_resized);
             // And finally write all we've found out to the original image!
             // First of all draw a green rectangle around the detected face:
-            rectangle(original, face_i, CV_RGB(0, 255,0), 1);
+            rectangle(original, face_i, Scalar(0, 255,0), 1);
             // Create the text we will annotate the box with:
             string box_text = format("Prediction = %d", prediction);
             // Calculate the position for annotated text (make sure we don't
@@ -139,7 +139,7 @@ int main(int argc, const char *argv[]) {
             int pos_x = std::max(face_i.tl().x - 10, 0);
             int pos_y = std::max(face_i.tl().y - 10, 0);
             // And now put it into the image:
-            putText(original, box_text, Point(pos_x, pos_y), FONT_HERSHEY_PLAIN, 1.0, CV_RGB(0,255,0), 2.0);
+            putText(original, box_text, Point(pos_x, pos_y), FONT_HERSHEY_PLAIN, 1.0, Scalar(0,255,0), 2);
         }
         // Show the result:
         imshow("face_recognizer", original);

modules/face/samples/src/facerec_demo.cpp

-/*
- * Copyright (c) 2011. Philipp Wagner <bytefish[at]gmx[dot]de>.
- * Released to public domain under terms of the BSD Simplified license.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in the
- *     documentation and/or other materials provided with the distribution.
- *   * Neither the name of the organization nor the names of its contributors
- *     may be used to endorse or promote products derived from this software
- *     without specific prior written permission.
- *
- *   See <http://www.opensource.org/licenses/bsd-license>
- */
-
-#include "opencv2/core.hpp"
-#include "opencv2/face.hpp"
-#include "opencv2/highgui.hpp"
-
-#include <iostream>
-#include <fstream>
-#include <sstream>
-
-using namespace cv;
-using namespace cv::face;
-using namespace std;
-
-static Mat norm_0_255(InputArray _src) {
-    Mat src = _src.getMat();
-    // Create and return normalized image:
-    Mat dst;
-    switch(src.channels()) {
-    case 1:
-        cv::normalize(_src, dst, 0, 255, NORM_MINMAX, CV_8UC1);
-        break;
-    case 3:
-        cv::normalize(_src, dst, 0, 255, NORM_MINMAX, CV_8UC3);
-        break;
-    default:
-        src.copyTo(dst);
-        break;
-    }
-    return dst;
-}
-
-static void read_csv(const string& filename, vector<Mat>& images, vector<int>& labels, char separator = ';') {
-    std::ifstream file(filename.c_str(), ifstream::in);
-    if (!file) {
-        string error_message = "No valid input file was given, please check the given filename.";
-        CV_Error(CV_StsBadArg, error_message);
-    }
-    string line, path, classlabel;
-    while (getline(file, line)) {
-        stringstream liness(line);
-        getline(liness, path, separator);
-        getline(liness, classlabel);
-        if(!path.empty() && !classlabel.empty()) {
-            images.push_back(imread(path, 0));
-            labels.push_back(atoi(classlabel.c_str()));
-        }
-    }
-}
-
-int main(int argc, const char *argv[]) {
-    // Check for valid command line arguments, print usage
-    // if no arguments were given.
-    if (argc != 2) {
-        cout << "usage: " << argv[0] << " <csv.ext>" << endl;
-        exit(1);
-    }
-    // Get the path to your CSV.
-    string fn_csv = string(argv[1]);
-    // These vectors hold the images and corresponding labels.
-    vector<Mat> images;
-    vector<int> labels;
-    // Read in the data. This can fail if no valid
-    // input filename is given.
-    try {
-        read_csv(fn_csv, images, labels);
-    } catch (cv::Exception& e) {
-        cerr << "Error opening file \"" << fn_csv << "\". Reason: " << e.msg << endl;
-        // nothing more we can do
-        exit(1);
-    }
-    // Quit if there are not enough images for this demo.
-    if(images.size() <= 1) {
-        string error_message = "This demo needs at least 2 images to work. Please add more images to your data set!";
-        CV_Error(CV_StsError, error_message);
-    }
-    // Get the height from the first image. We'll need this
-    // later in code to reshape the images to their original
-    // size:
-    int height = images[0].rows;
-    // The following lines simply get the last images from
-    // your dataset and remove it from the vector. This is
-    // done, so that the training data (which we learn the
-    // cv::FaceRecognizer on) and the test data we test
-    // the model with, do not overlap.
-    Mat testSample = images[images.size() - 1];
-    int testLabel = labels[labels.size() - 1];
-    images.pop_back();
-    labels.pop_back();
-    // The following lines create an Eigenfaces model for
-    // face recognition and train it with the images and
-    // labels read from the given CSV file.
-    // This here is a full PCA, if you just want to keep
-    // 10 principal components (read Eigenfaces), then call
-    // the factory method like this:
-    //
-    //      cv::createEigenFaceRecognizer(10);
-    //
-    // If you want to create a FaceRecognizer with a
-    // confidennce threshold, call it with:
-    //
-    //      cv::createEigenFaceRecognizer(10, 123.0);
-    //
-    Ptr<FaceRecognizer> model = createFisherFaceRecognizer();
-    model->train(images, labels);
-    // The following line predicts the label of a given
-    // test image:
-    int predictedLabel = model->predict(testSample);
-    //
-    // To get the confidence of a prediction call the model with:
-    //
-    //      int predictedLabel = -1;
-    //      double confidence = 0.0;
-    //      model->predict(testSample, predictedLabel, confidence);
-    //
-    string result_message = format("Predicted class = %d / Actual class = %d.", predictedLabel, testLabel);
-    cout << result_message << endl;
-    // Sometimes you'll need to get/set internal model data,
-    // which isn't exposed by the public cv::FaceRecognizer.
-    // Since each cv::FaceRecognizer is derived from a
-    // cv::Algorithm, you can query the data.
-    //
-    // First we'll use it to set the threshold of the FaceRecognizer
-    // to 0.0 without retraining the model. This can be useful if
-    // you are evaluating the model:
-    //
-    model->set("threshold", 0.0);
-    // Now the threshold of this model is set to 0.0. A prediction
-    // now returns -1, as it's impossible to have a distance below
-    // it
-    predictedLabel = model->predict(testSample);
-    cout << "Predicted class = " << predictedLabel << endl;
-    // Here is how to get the eigenvalues of this Eigenfaces model:
-    Mat eigenvalues = model->getMat("eigenvalues");
-    // And we can do the same to display the Eigenvectors (read Eigenfaces):
-    Mat W = model->getMat("eigenvectors");
-    // From this we will display the (at most) first 10 Eigenfaces:
-    for (int i = 0; i < min(10, W.cols); i++) {
-        string msg = format("Eigenvalue #%d = %.5f", i, eigenvalues.at<double>(i));
-        cout << msg << endl;
-        // get eigenvector #i
-        Mat ev = W.col(i).clone();
-        // Reshape to original size & normalize to [0...255] for imshow.
-        Mat grayscale = norm_0_255(ev.reshape(1, height));
-        // Show the image & apply a Jet colormap for better sensing.
-        Mat cgrayscale;
-        applyColorMap(grayscale, cgrayscale, COLORMAP_JET);
-        imshow(format("%d", i), cgrayscale);
-    }
-    waitKey(0);
-
-    return 0;
-}

modules/face/tutorials/face_tutorial.markdown

@@ -246,7 +246,7 @@ every source code listing is commented in detail, so you should have no problems
 The source code for this demo application is also available in the src folder coming with this
 documentation:
 
-@include src/facerec_eigenfaces.cpp
+@include face/samples/facerec_eigenfaces.cpp
 
 I've used the jet colormap, so you can see how the grayscale values are distributed within the
 specific Eigenfaces. You can see, that the Eigenfaces do not only encode facial features, but also
@@ -263,8 +263,8 @@ let's see how many Eigenfaces are needed for a good reconstruction. I'll do a su
 for(int num_components = 10; num_components < 300; num_components+=15) {
     // slice the eigenvectors from the model
     Mat evs = Mat(W, Range::all(), Range(0, num_components));
-    Mat projection = subspaceProject(evs, mean, images[0].reshape(1,1));
-    Mat reconstruction = subspaceReconstruct(evs, mean, projection);
+    Mat projection = LDA::subspaceProject(evs, mean, images[0].reshape(1,1));
+    Mat reconstruction = LDA::subspaceReconstruct(evs, mean, projection);
     // Normalize the result:
     reconstruction = norm_0_255(reconstruction.reshape(1, images[0].rows));
     // Display or save:
@@ -370,7 +370,7 @@ given by:
 The source code for this demo application is also available in the src folder coming with this
 documentation:
 
-@include src/facerec_fisherfaces.cpp
+@include face/samples/facerec_fisherfaces.cpp
 
 For this example I am going to use the Yale Facedatabase A, just because the plots are nicer. Each
 Fisherface has the same length as an original image, thus it can be displayed as an image. The demo
@@ -398,8 +398,8 @@ Fisherfaces describes:
 for(int num_component = 0; num_component < min(16, W.cols); num_component++) {
     // Slice the Fisherface from the model:
     Mat ev = W.col(num_component);
-    Mat projection = subspaceProject(ev, mean, images[0].reshape(1,1));
-    Mat reconstruction = subspaceReconstruct(ev, mean, projection);
+    Mat projection = LDA::subspaceProject(ev, mean, images[0].reshape(1,1));
+    Mat reconstruction = LDA::subspaceReconstruct(ev, mean, projection);
     // Normalize the result:
     reconstruction = norm_0_255(reconstruction.reshape(1, images[0].rows));
     // Display or save:
@@ -528,7 +528,7 @@ Patterns Histograms*.
 The source code for this demo application is also available in the src folder coming with this
 documentation:
 
-@include src/facerec_lbph.cpp
+@include face/samples/facerec_lbph.cpp
 
 Conclusion {#tutorial_face_conclusion}
 ----------
@@ -658,7 +658,7 @@ at/s17/3.pgm;1
 
 Here is the script, if you can't find it:
 
-@verbinclude face/samples/src/create_csv.py
+@verbinclude face/samples/etc/create_csv.py
 
 ### Aligning Face Images {#tutorial_face_appendix_align}
 
@@ -677,7 +677,7 @@ where:
 If you are using the same *offset_pct* and *dest_sz* for your images, they are all aligned at the
 eyes.
 
-@verbinclude face/samples/src/crop_face.py
+@verbinclude face/samples/etc/crop_face.py
 
 Imagine we are given [this photo of Arnold
 Schwarzenegger](http://en.wikipedia.org/wiki/File:Arnold_Schwarzenegger_edit%28ws%29.jpg), which is

modules/line_descriptor/src/LSDDetector.cpp

@@ -203,7 +203,10 @@ void LSDDetector::detectImpl( const Mat& imageSrc, std::vector<KeyLine>& keyline
     {
       KeyLine kl = keylines[keyCounter];
       if( mask.at<uchar>( (int) kl.startPointY, (int) kl.startPointX ) == 0 && mask.at<uchar>( (int) kl.endPointY, (int) kl.endPointX ) == 0 )
+      {
         keylines.erase( keylines.begin() + keyCounter );
+        keyCounter--;
+      }
     }
   }
 

modules/line_descriptor/src/binary_descriptor.cpp

@@ -41,6 +41,19 @@
 
 #include "precomp.hpp"
 
+#ifdef _MSC_VER
+    #if (_MSC_VER <= 1700)
+        /* This function rounds x to the nearest integer, but rounds halfway cases away from zero. */
+        static inline double round(double x)
+        {
+            if (x < 0.0)
+                return ceil(x - 0.5);
+            else
+                return floor(x + 0.5);
+        }
+    #endif
+#endif
+
 #define NUM_OF_BANDS 9
 #define Horizontal  255//if |dx|<|dy|;
 #define Vertical    0//if |dy|<=|dx|;

modules/line_descriptor/src/bitops.hpp

@@ -101,7 +101,7 @@ inline void split( UINT64 *chunks, UINT8 *code, int m, int mplus, int b )
   UINT64 temp = 0x0;
   int nbits = 0;
   int nbyte = 0;
-  UINT64 mask = b == 64 ? 0xFFFFFFFFFFFFFFFFLLU : ( ( UINT64_1 << b ) - UINT64_1 );
+  UINT64 mask = (b == 64) ? 0xFFFFFFFFFFFFFFFFull : ( ( UINT64_1 << b ) - UINT64_1 );
 
   for ( int i = 0; i < m; i++ )
   {

modules/saliency/src/motionSaliencyBinWangApr2014.cpp

@@ -479,7 +479,7 @@ bool MotionSaliencyBinWangApr2014::templateReplacement( const Mat& finalBFMask,
                 /////////////////// REPLACEMENT of backgroundModel template ///////////////////
                 //replace TA with current TK
                 backgroundModel[backgroundModel.size() - 1]->at<Vec2f>( i, j ) = potentialBackground.at<Vec2f>( i, j );
-                potentialBackground.at<Vec2f>( i, j )[0] = NAN;
+                potentialBackground.at<Vec2f>( i, j )[0] = (float)NAN;
                 potentialBackground.at<Vec2f>( i, j )[1] = 0;
 
                 break;
@@ -489,7 +489,7 @@ bool MotionSaliencyBinWangApr2014::templateReplacement( const Mat& finalBFMask,
           else
           {
             backgroundModel[backgroundModel.size() - 1]->at<Vec2f>( i, j ) = potentialBackground.at<Vec2f>( i, j );
-            potentialBackground.at<Vec2f>( i, j )[0] = NAN;
+            potentialBackground.at<Vec2f>( i, j )[0] = (float)NAN;
             potentialBackground.at<Vec2f>( i, j )[1] = 0;
           }
         }  // close if of EVALUATION

modules/stereo/CMakeLists.txt

+set(the_description "Stereo Correspondence")
+ocv_define_module(stereo opencv_imgproc opencv_features2d opencv_core opencv_highgui opencv_calib3d)

modules/stereo/README.md

+Stereo Correspondence with different descriptors
+================================================

modules/stereo/include/opencv2/stereo/stereo.hpp

+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                          License Agreement
+//                For Open Source Computer Vision Library
+//
+// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
+// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
+// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of the copyright holders may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Intel Corporation or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#ifdef __OPENCV_BUILD
+#error this is a compatibility header which should not be used inside the OpenCV library
+#endif
+
+#include "opencv2/stereo.hpp"
+

modules/stereo/src/precomp.hpp

+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                          License Agreement
+//                For Open Source Computer Vision Library
+//
+// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
+// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of the copyright holders may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Intel Corporation or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+#ifndef __OPENCV_STEREO_PRECOMP_H__
+#define __OPENCV_STEREO_PRECOMP_H__
+
+#include "opencv2/stereo.hpp"
+#include "opencv2/imgproc.hpp"
+#include "opencv2/features2d.hpp"
+#include "opencv2/core.hpp"
+#include "opencv2/core/utility.hpp"
+#include "opencv2/core/private.hpp"
+#include "opencv2/core/cvdef.h"
+#include "opencv2/highgui.hpp"
+#include "opencv2/calib3d.hpp"
+
+#include <algorithm>
+#include <cmath>
+
+#endif
+

modules/stereo/test/test_main.cpp

+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                           License Agreement
+//                For Open Source Computer Vision Library
+//
+// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
+// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of the copyright holders may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Intel Corporation or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#include "test_precomp.hpp"
+
+CV_TEST_MAIN("cv")

modules/stereo/test/test_precomp.hpp

+#ifdef __GNUC__
+#  pragma GCC diagnostic ignored "-Wmissing-declarations"
+#  if defined __clang__ || defined __APPLE__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
+#endif
+
+#ifndef __OPENCV_TEST_PRECOMP_HPP__
+#define __OPENCV_TEST_PRECOMP_HPP__
+
+#include <iostream>
+#include "opencv2/ts.hpp"
+#include "opencv2/imgcodecs.hpp"
+
+
+#include "opencv2/stereo.hpp"
+#include "opencv2/imgproc.hpp"
+#include "opencv2/features2d.hpp"
+#include "opencv2/core/utility.hpp"
+#include "opencv2/core/private.hpp"
+#include "opencv2/core/cvdef.h"
+#include "opencv2/core.hpp"
+#include "opencv2/highgui.hpp"
+
+#include <algorithm>
+#include <cmath>
+
+
+
+#endif

modules/surface_matching/samples/ppf_load_match.cpp

@@ -110,9 +110,22 @@ int main(int argc, char** argv)
     tick2 = cv::getTickCount();
     cout << endl << "PPF Elapsed Time " <<
          (tick2-tick1)/cv::getTickFrequency() << " sec" << endl;
-         
-    // Get only first N results
-    int N = 2;
+
+    //check results size from match call above
+    size_t results_size = results.size();
+    cout << "Number of matching poses: " << results_size;
+    if (results_size == 0) {
+        cout << endl << "No matching poses found. Exiting." << endl;
+        exit(0);
+    }
+
+    // Get only first N results - but adjust to results size if num of results are less than that specified by N
+    size_t N = 2;
+    if (results_size < N) {
+        cout << endl << "Reducing matching poses to be reported (as specified in code): "
+             << N << " to the number of matches found: " << results_size << endl;
+        N = results_size;
+    }
     vector<Pose3DPtr> resultsSub(results.begin(),results.begin()+N);
     
     // Create an instance of ICP

modules/surface_matching/src/ppf_match_3d.cpp

@@ -375,7 +375,7 @@ void PPF3DDetector::clusterPoses(std::vector<Pose3DPtr> poseList, int numPoses,
 #pragma omp parallel for
 #endif
     // uses weighting by the number of votes
-    for (size_t i=0; i<poseClusters.size(); i++)
+    for (int i=0; i<static_cast<int>(poseClusters.size()); i++)
     {
       // We could only average the quaternions. So I will make use of them here
       double qAvg[4]={0}, tAvg[3]={0};
@@ -426,7 +426,7 @@ void PPF3DDetector::clusterPoses(std::vector<Pose3DPtr> poseList, int numPoses,
 #if defined _OPENMP
 #pragma omp parallel for
 #endif
-    for (size_t i=0; i<poseClusters.size(); i++)
+    for (int i=0; i<static_cast<int>(poseClusters.size()); i++)
     {
       // We could only average the quaternions. So I will make use of them here
       double qAvg[4]={0}, tAvg[3]={0};

modules/text/samples/cropped_word_recognition.cpp

+/*
+ * cropped_word_recognition.cpp
+ *
+ * A demo program of text recognition in a given cropped word.
+ * Shows the use of the OCRBeamSearchDecoder class API using the provided default classifier.
+ *
+ * Created on: Jul 9, 2015
+ *     Author: Lluis Gomez i Bigorda <lgomez AT cvc.uab.es>
+ */
+
+#include "opencv2/text.hpp"
+#include "opencv2/core/utility.hpp"
+#include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
+
+#include <iostream>
+
+using namespace std;
+using namespace cv;
+using namespace cv::text;
+
+int main(int argc, char* argv[])
+{
+
+    cout << endl << argv[0] << endl << endl;
+    cout << "A demo program of Scene Text cropped word Recognition: " << endl;
+    cout << "Shows the use of the OCRBeamSearchDecoder class using the Single Layer CNN character classifier described in:" << endl;
+    cout << "Coates, Adam, et al. \"Text detection and character recognition in scene images with unsupervised feature learning.\" ICDAR 2011." << endl << endl;
+
+    Mat image;
+    if(argc>1)
+        image  = imread(argv[1]);
+    else
+    {
+        cout << "    Usage: " << argv[0] << " <input_image>" << endl << endl;
+        return(0);
+    }
+
+    string vocabulary = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"; // must have the same order as the clasifier output classes
+    vector<string> lexicon;  // a list of words expected to be found on the input image
+    lexicon.push_back(string("abb"));
+    lexicon.push_back(string("patata"));
+    lexicon.push_back(string("CHINA"));
+    lexicon.push_back(string("HERE"));
+    lexicon.push_back(string("President"));
+    lexicon.push_back(string("smash"));
+    lexicon.push_back(string("KUALA"));
+    lexicon.push_back(string("NINTENDO"));
+
+    // Create tailored language model a small given lexicon
+    Mat transition_p;
+    createOCRHMMTransitionsTable(vocabulary,lexicon,transition_p);
+
+    // An alternative would be to load the default generic language model
+    //    (created from ispell 42869 english words list)
+    /*Mat transition_p;
+    string filename = "OCRHMM_transitions_table.xml"; // TODO use same order for voc
+    FileStorage fs(filename, FileStorage::READ);
+    fs["transition_probabilities"] >> transition_p;
+    fs.release();*/
+
+    Mat emission_p = Mat::eye(62,62,CV_64FC1);
+
+    Ptr<OCRBeamSearchDecoder> ocr = OCRBeamSearchDecoder::create(
+                loadOCRBeamSearchClassifierCNN("OCRBeamSearch_CNN_model_data.xml.gz"),
+                vocabulary, transition_p, emission_p);
+
+    double t_r = (double)getTickCount();
+    string output;
+
+    vector<Rect>   boxes;
+    vector<string> words;
+    vector<float>  confidences;
+    ocr->run(image, output, &boxes, &words, &confidences, OCR_LEVEL_WORD);
+
+    cout << "OCR output = \"" << output << "\". Decoded in "
+         << ((double)getTickCount() - t_r)*1000/getTickFrequency() << " ms." << endl << endl;
+
+    return 0;
+}

modules/text/src/erfilter.cpp

@@ -287,7 +287,11 @@ void ERFilterNM::er_tree_extract( InputArray image )
     quads[1][3] = (1<<3)|(1<<2)|(1<<1);
     quads[2][0] = (1<<2)|(1<<1);
     quads[2][1] = (1<<3)|(1);
-    quads[2][3] = 255;
+    // quads[2][2] and quads[2][3] are never used so no need to initialize them.
+    // The four lowest bits in each quads[i][j] correspond to the 2x2 binary patterns 
+    // Q_1, Q_2, Q_3 in the Neumann and Matas CVPR 2012 paper 
+    // (see in page 4 at the end of first column). 
+    // Q_1 and Q_2 have four patterns, while Q_3 has only two.
 
 
     // masks to know if a pixel is accessible and if it has been already added to some region

modules/text/src/ocr_tesseract.cpp

@@ -70,6 +70,22 @@ void OCRTesseract::run(Mat& image, string& output_text, vector<Rect>* component_
         component_confidences->clear();
 }
 
+void OCRTesseract::run(Mat& image, Mat& mask, string& output_text, vector<Rect>* component_rects,
+                       vector<string>* component_texts, vector<float>* component_confidences,
+                       int component_level)
+{
+    CV_Assert( (image.type() == CV_8UC1) || (image.type() == CV_8UC3) );
+    CV_Assert( mask.type() == CV_8UC1 );
+    CV_Assert( (component_level == OCR_LEVEL_TEXTLINE) || (component_level == OCR_LEVEL_WORD) );
+    output_text.clear();
+    if (component_rects != NULL)
+        component_rects->clear();
+    if (component_texts != NULL)
+        component_texts->clear();
+    if (component_confidences != NULL)
+        component_confidences->clear();
+}
+
 class OCRTesseractImpl : public OCRTesseract
 {
 private:
@@ -127,7 +143,7 @@ public:
              int component_level=0)
     {
 
-        CV_Assert( (image.type() == CV_8UC1) || (image.type() == CV_8UC1) );
+        CV_Assert( (image.type() == CV_8UC1) || (image.type() == CV_8UC3) );
 
 #ifdef HAVE_TESSERACT
 
@@ -140,7 +156,10 @@ public:
 
         tess.SetImage((uchar*)image.data, image.size().width, image.size().height, image.channels(), image.step1());
         tess.Recognize(0);
-        output = string(tess.GetUTF8Text());
+        char *outText;
+        outText = tess.GetUTF8Text();
+        output = string(outText);
+        delete [] outText;
 
         if ( (component_rects != NULL) || (component_texts != NULL) || (component_confidences != NULL) )
         {
@@ -186,6 +205,16 @@ public:
 #endif
     }
 
+    void run(Mat& image, Mat& mask, string& output, vector<Rect>* component_rects=NULL,
+             vector<string>* component_texts=NULL, vector<float>* component_confidences=NULL,
+             int component_level=0)
+    {
+        CV_Assert( mask.type() == CV_8UC1 );
+        CV_Assert( (image.type() == CV_8UC1) || (image.type() == CV_8UC3) );
+
+        run( mask, output, component_rects, component_texts, component_confidences, component_level);
+    }
+
 
 };
 

modules/tracking/doc/tracking.bib

@@ -67,3 +67,29 @@
   year={2013},
   organization={IEEE}
 }
+
+@article{KCF,
+  title = {High-Speed Tracking with Kernelized Correlation Filters},
+  journal = {Pattern Analysis and Machine Intelligence, IEEE Transactions on},
+  author = {Henriques, J. F. and Caseiro, R. and Martins, P. and Batista, J.},
+  year = {2015},
+  doi = {10.1109/TPAMI.2014.2345390},
+}
+
+@inproceedings{KCF_ECCV,
+  title = {Exploiting the Circulant Structure of Tracking-by-detection with Kernels},
+  author = {Henriques, J. F. and Caseiro, R. and Martins, P. and Batista, J.},
+  booktitle = {proceedings of the European Conference on Computer Vision},
+  year = {2012},
+}
+
+@INPROCEEDINGS{KCF_CN,
+  author={Danelljan, M. and Khan, F.S. and Felsberg, M. and van de Weijer, J.},
+  booktitle={Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on},
+  title={Adaptive Color Attributes for Real-Time Visual Tracking},
+  year={2014},
+  month={June},
+  pages={1090-1097},
+  keywords={computer vision;feature extraction;image colour analysis;image representation;image sequences;adaptive color attributes;benchmark color sequences;color features;color representations;computer vision;image description;real-time visual tracking;tracking-by-detection framework;Color;Computational modeling;Covariance matrices;Image color analysis;Kernel;Target tracking;Visualization;Adaptive Dimensionality Reduction;Appearance Model;Color Features;Visual Tracking},
+  doi={10.1109/CVPR.2014.143},
+}

modules/tracking/src/tldEnsembleClassifier.hpp

@@ -64,6 +64,5 @@ namespace cv
 			std::vector<Point2i> offset;
 			int lastStep_;
 		};
-
 	}
 }
\ No newline at end of file