Skip to content

O
opencv_contrib
Commit 076f53d6 authored by StevenPuttemans's avatar StevenPuttemans
Browse files
Options

fixing facerecognizer tutorials and interface

parent aa11ac48
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 59 additions and 402 deletions
modules/face/CMakeLists.txt
View file @ 076f53d6
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/etc/at.txt deleted 100644 → 0
View file @ aa11ac48
This diff is collapsed.
modules/face/doc/src/facerec_demo.cpp deleted 100644 → 0
View file @ aa11ac48
/*
* 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/facerec_at_t.txt deleted 100644 → 0
View file @ aa11ac48
This diff is collapsed.
modules/face/samples/src/facerec_eigenfaces.cpp → modules/face/samples/facerec_eigenfaces.cpp
View file @ 076f53d6
......@@ -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
View file @ 076f53d6
......@@ -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
View file @ 076f53d6
......@@ -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
View file @ 076f53d6
......@@ -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
View file @ 076f53d6
......@@ -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 deleted 100755 → 0
View file @ aa11ac48
/*
* 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
View file @ 076f53d6
......@@ -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
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment