Skip to content

O
opencv_contrib
Commit 1a9a3fdc authored by Suleyman TURKMEN's avatar Suleyman TURKMEN
Browse files
Options

Update webcam_demo.cpp

parent e7547d61
Hide whitespace changes
Inline Side-by-side
Showing with 134 additions and 136 deletions
modules/text/samples/webcam_demo.cpp
View file @ 1a9a3fdc
/*
* webcam-demo.cpp
*
* A demo program of End-to-end Scene Text Detection and Recognition.
* A demo program of End-to-end Scene Text Detection and Recognition using webcam or video.
*
* Created on: Jul 31, 2014
* 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 "opencv2/features2d.hpp"
#include <iostream>
using namespace std;
using namespace cv;
using namespace cv::text;
......@@ -32,7 +30,7 @@ private:
public:
Parallel_extractCSER(vector<Mat> &_channels, vector< vector<ERStat> > &_regions,
vector<Ptr<ERFilter> >_er_filter1, vector<Ptr<ERFilter> >_er_filter2)
: channels(_channels),regions(_regions),er_filter1(_er_filter1),er_filter2(_er_filter2){}
: channels(_channels),regions(_regions),er_filter1(_er_filter1),er_filter2(_er_filter2) {}
virtual void operator()( const cv::Range &r ) const
{
......@@ -75,34 +73,81 @@ public:
Parallel_OCR & operator=(const Parallel_OCR &a);
};
//Discard wrongly recognised strings
bool isRepetitive(const string& s);
//Draw ER's in an image via floodFill
void er_draw(vector<Mat> &channels, vector<vector<ERStat> > &regions, vector<Vec2i> group, Mat& segmentation);
//Perform text detection and recognition from webcam
const char* keys =
{
"{@input | 0 | camera index or video file name}"
"{ image i | | specify input image}"
};
//Perform text detection and recognition from webcam or video
int main(int argc, char* argv[])
{
cout << endl << argv[0] << endl << endl;
cout << "A demo program of End-to-end Scene Text Detection and Recognition using webcam." << endl << endl;
cout << " Usage: " << argv[0] << " [camera_index]" << endl << endl;
CommandLineParser parser(argc, argv, keys);
cout << "A demo program of End-to-end Scene Text Detection and Recognition using webcam or video." << endl << endl;
cout << " Keys: " << endl;
cout << " Press 'r' to switch between MSER/CSER regions." << endl;
cout << " Press 'g' to switch between Horizontal and Arbitrary oriented grouping." << endl;
cout << " Press 'o' to switch between OCRTesseract/OCRHMMDecoder recognition." << endl;
cout << " Press 's' to scale down frame size to 320x240." << endl;
cout << " Press 'ESC' to exit." << endl << endl;
parser.printMessage();
VideoCapture cap;
Mat frame, image, gray, out_img;
String input = parser.get<String>("@input");
String image_file_name = parser.get<String>("image");
if (image_file_name != "")
{
image = imread(image_file_name);
if (image.empty())
{
cout << "\nunable to open " << image_file_name << "\nprogram terminated!\n";
return 1;
}
else
{
cout << "\nimage " << image_file_name << " loaded!\n";
frame = image.clone();
}
}
else
{
cout << "\nInitializing capturing... ";
if (input.size() == 1 && isdigit(input[0]))
cap.open(input[0] - '0');
else
cap.open(input);
if (!cap.isOpened())
{
cout << "\nCould not initialize capturing!\n";
return 1;
}
cout << " Done!" << endl;
cap.read(frame);
}
namedWindow("recognition",WINDOW_NORMAL);
imshow("recognition", frame);
waitKey(1);
bool downsize = false;
int REGION_TYPE = 1;
int GROUPING_ALGORITHM = 0;
int RECOGNITION = 0;
char *region_types_str[2] = {const_cast<char *>("ERStats"), const_cast<char *>("MSER")};
char *grouping_algorithms_str[2] = {const_cast<char *>("exhaustive_search"), const_cast<char *>("multioriented")};
char *recognitions_str[2] = {const_cast<char *>("Tesseract"), const_cast<char *>("NM_chain_features + KNN")};
Mat frame,grey,orig_grey,out_img;
String region_types_str[2] = {"ERStats", "MSER"};
String grouping_algorithms_str[2] = {"exhaustive_search", "multioriented"};
String recognitions_str[2] = {"Tesseract", "NM_chain_features + KNN"};
vector<Mat> channels;
vector<vector<ERStat> > regions(2); //two channels
......@@ -118,15 +163,13 @@ int main(int argc, char* argv[])
er_filters2.push_back(er_filter2);
}
//double t_r = getTickCount();
//Initialize OCR engine (we initialize 10 instances in order to work several recognitions in parallel)
cout << "Initializing OCR engines ..." << endl;
cout << "Initializing OCR engines ... ";
int num_ocrs = 10;
vector< Ptr<OCRTesseract> > ocrs;
for (int o=0; o<num_ocrs; o++)
{
ocrs.push_back(OCRTesseract::create());
ocrs.push_back(OCRTesseract::create());
}
Mat transition_p;
......@@ -140,26 +183,12 @@ int main(int argc, char* argv[])
vector< Ptr<OCRHMMDecoder> > decoders;
for (int o=0; o<num_ocrs; o++)
{
decoders.push_back(OCRHMMDecoder::create(loadOCRHMMClassifierNM("OCRHMM_knn_model_data.xml.gz"),
voc, transition_p, emission_p));
decoders.push_back(OCRHMMDecoder::create(loadOCRHMMClassifierNM("OCRHMM_knn_model_data.xml.gz"),
voc, transition_p, emission_p));
}
cout << " Done!" << endl;
//cout << "TIME_OCR_INITIALIZATION_ALT = "<< ((double)getTickCount() - t_r)*1000/getTickFrequency() << endl;
int cam_idx = 0;
if (argc > 1)
cam_idx = atoi(argv[1]);
VideoCapture cap(cam_idx);
if(!cap.isOpened())
{
cout << "ERROR: Cannot open default camera (0)." << endl;
return -1;
}
while (cap.read(frame))
while ( true )
{
double t_all = (double)getTickCount();
......@@ -167,93 +196,65 @@ int main(int argc, char* argv[])
resize(frame,frame,Size(320,240));
/*Text Detection*/
cvtColor(frame,grey,COLOR_RGB2GRAY);
grey.copyTo(orig_grey);
cvtColor(frame,gray,COLOR_BGR2GRAY);
// Extract channels to be processed individually
channels.clear();
channels.push_back(grey);
channels.push_back(255-grey);
channels.push_back(gray);
channels.push_back(255-gray);
regions[0].clear();
regions[1].clear();
//double t_d = (double)getTickCount();
switch (REGION_TYPE)
{
case 0:
{
parallel_for_(cv::Range(0,(int)channels.size()), Parallel_extractCSER(channels,regions,er_filters1,er_filters2));
case 0: // ERStats
parallel_for_(cv::Range(0, (int)channels.size()), Parallel_extractCSER(channels, regions, er_filters1, er_filters2));
break;
}
case 1:
{
//Extract MSER
case 1: // MSER
vector<vector<Point> > contours;
vector<Rect> bboxes;
Ptr<MSER> mser = MSER::create(21,(int)(0.00002*grey.cols*grey.rows),(int)(0.05*grey.cols*grey.rows),1,0.7);
mser->detectRegions(grey, contours, bboxes);
Ptr<MSER> mser = MSER::create(21, (int)(0.00002*gray.cols*gray.rows), (int)(0.05*gray.cols*gray.rows), 1, 0.7);
mser->detectRegions(gray, contours, bboxes);
//Convert the output of MSER to suitable input for the grouping/recognition algorithms
if (contours.size() > 0)
MSERsToERStats(grey, contours, regions);
MSERsToERStats(gray, contours, regions);
break;
}
case 2:
{
break;
}
}
//cout << "TIME_REGION_DETECTION_ALT = " << ((double)getTickCount() - t_d)*1000/getTickFrequency() << endl;
// Detect character groups
//double t_g = getTickCount();
vector< vector<Vec2i> > nm_region_groups;
vector<Rect> nm_boxes;
switch (GROUPING_ALGORITHM)
{
case 0:
{
case 0: // exhaustive_search
erGrouping(frame, channels, regions, nm_region_groups, nm_boxes, ERGROUPING_ORIENTATION_HORIZ);
break;
}
case 1:
{
case 1: //multioriented
erGrouping(frame, channels, regions, nm_region_groups, nm_boxes, ERGROUPING_ORIENTATION_ANY, "./trained_classifier_erGrouping.xml", 0.5);
break;
}
}
//cout << "TIME_GROUPING_ALT = " << ((double)getTickCount() - t_g)*1000/getTickFrequency() << endl;
/*Text Recognition (OCR)*/
frame.copyTo(out_img);
int scale = downsize ? 2 : 1;
float scale_img = (float)((600.f/frame.rows)/scale);
float scale_font = (float)(2-scale_img)/1.4f;
int bottom_bar_height= out_img.rows/7 ;
copyMakeBorder(frame, out_img, 0, bottom_bar_height, 0, 0, BORDER_CONSTANT, Scalar(150, 150, 150));
float scale_font = (float)(bottom_bar_height /85.0);
vector<string> words_detection;
float min_confidence1 = 0.f, min_confidence2 = 0.f;
if (RECOGNITION == 0)
{
min_confidence1 = 51.f; min_confidence2 = 60.f;
min_confidence1 = 51.f;
min_confidence2 = 60.f;
}
vector<Mat> detections;
//t_r = getTickCount();
for (int i=0; i<(int)nm_boxes.size(); i++)
{
rectangle(out_img, nm_boxes[i].tl(), nm_boxes[i].br(), Scalar(255,255,0),3);
Mat group_img = Mat::zeros(frame.rows+2, frame.cols+2, CV_8UC1);
er_draw(channels, regions, nm_region_groups[i], group_img);
group_img(nm_boxes[i]).copyTo(group_img);
......@@ -268,27 +269,25 @@ int main(int argc, char* argv[])
// parallel process detections in batches of ocrs.size() (== num_ocrs)
for (int i=0; i<(int)detections.size(); i=i+(int)num_ocrs)
{
Range r;
if (i+(int)num_ocrs <= (int)detections.size())
r = Range(i,i+(int)num_ocrs);
else
r = Range(i,(int)detections.size());
switch(RECOGNITION)
{
case 0:
parallel_for_(r, Parallel_OCR<OCRTesseract>(detections, outputs, boxes, words, confidences, ocrs));
break;
case 1:
parallel_for_(r, Parallel_OCR<OCRHMMDecoder>(detections, outputs, boxes, words, confidences, decoders));
break;
}
}
Range r;
if (i+(int)num_ocrs <= (int)detections.size())
r = Range(i,i+(int)num_ocrs);
else
r = Range(i,(int)detections.size());
switch(RECOGNITION)
{
case 0: // Tesseract
parallel_for_(r, Parallel_OCR<OCRTesseract>(detections, outputs, boxes, words, confidences, ocrs));
break;
case 1: // NM_chain_features + KNN
parallel_for_(r, Parallel_OCR<OCRHMMDecoder>(detections, outputs, boxes, words, confidences, decoders));
break;
}
}
for (int i=0; i<(int)detections.size(); i++)
{
outputs[i].erase(remove(outputs[i].begin(), outputs[i].end(), '\n'), outputs[i].end());
//cout << "OCR output = \"" << outputs[i] << "\" length = " << outputs[i].size() << endl;
if (outputs[i].size() < 3)
......@@ -311,56 +310,57 @@ int main(int argc, char* argv[])
rectangle(out_img, boxes[i][j].tl()-Point(3,word_size.height+3), boxes[i][j].tl()+Point(word_size.width,0), Scalar(255,0,255),-1);
putText(out_img, words[i][j], boxes[i][j].tl()-Point(1,1), FONT_HERSHEY_SIMPLEX, scale_font, Scalar(255,255,255),(int)(3*scale_font));
}
}
//cout << "TIME_OCR_ALT = " << ((double)getTickCount() - t_r)*1000/getTickFrequency() << endl;
t_all = ((double)getTickCount() - t_all)*1000/getTickFrequency();
char buff[100];
sprintf(buff, "%2.1f Fps. @ %dx%d", (float)(1000/t_all), out_img.cols, out_img.rows);
string fps_info = buff;
rectangle(out_img, Point( out_img.rows-(160/scale),out_img.rows-(70/scale) ), Point(out_img.cols,out_img.rows), Scalar(255,255,255),-1);
putText(out_img, fps_info, Point( 10,out_img.rows-(10/scale) ), FONT_HERSHEY_DUPLEX, scale_font, Scalar(255,0,0));
putText(out_img, region_types_str[REGION_TYPE], Point( out_img.rows-(150/scale),out_img.rows-(50/scale) ), FONT_HERSHEY_DUPLEX, scale_font, Scalar(255,0,0));
putText(out_img, grouping_algorithms_str[GROUPING_ALGORITHM], Point( out_img.rows-(150/scale),out_img.rows-(30/scale) ), FONT_HERSHEY_DUPLEX, scale_font, Scalar(255,0,0));
putText(out_img, recognitions_str[RECOGNITION], Point( out_img.rows-(150/scale),out_img.rows-(10/scale) ), FONT_HERSHEY_DUPLEX, scale_font, Scalar(255,0,0));
int text_thickness = 1+(out_img.rows/500);
string fps_info = format("%2.1f Fps. %dx%d", (float)(1000 / t_all), frame.cols, frame.rows);
putText(out_img, fps_info, Point( 10,out_img.rows-5 ), FONT_HERSHEY_DUPLEX, scale_font, Scalar(255,0,0), text_thickness);
putText(out_img, region_types_str[REGION_TYPE], Point((int)(out_img.cols*0.5), out_img.rows - (int)(bottom_bar_height / 1.5)), FONT_HERSHEY_DUPLEX, scale_font, Scalar(255,0,0), text_thickness);
putText(out_img, grouping_algorithms_str[GROUPING_ALGORITHM], Point((int)(out_img.cols*0.5),out_img.rows-((int)(bottom_bar_height /3)+4) ), FONT_HERSHEY_DUPLEX, scale_font, Scalar(255,0,0), text_thickness);
putText(out_img, recognitions_str[RECOGNITION], Point((int)(out_img.cols*0.5),out_img.rows-5 ), FONT_HERSHEY_DUPLEX, scale_font, Scalar(255,0,0), text_thickness);
imshow("recognition", out_img);
//imwrite("recognition_alt.jpg", out_img);
int key = waitKey(30);
if (key == 27) //wait for key
if ((image_file_name == "") && !cap.read(frame))
{
cout << "esc key pressed" << endl;
break;
cout << "Capturing ended! press any key to exit." << endl;
waitKey();
return 0;
}
else
int key = waitKey(30); //wait for a key press
switch (key)
{
switch (key)
case 27: //ESC
cout << "ESC key pressed and exited." << endl;
return 0;
case 32: //SPACE
imwrite("recognition_alt.jpg", out_img);
break;
case 103: //'g'
GROUPING_ALGORITHM = (GROUPING_ALGORITHM+1)%2;
cout << "Grouping switched to " << grouping_algorithms_str[GROUPING_ALGORITHM] << endl;
break;
case 111: //'o'
RECOGNITION = (RECOGNITION+1)%2;
cout << "OCR switched to " << recognitions_str[RECOGNITION] << endl;
break;
case 114: //'r'
REGION_TYPE = (REGION_TYPE+1)%2;
cout << "Regions switched to " << region_types_str[REGION_TYPE] << endl;
break;
case 115: //'s'
downsize = !downsize;
if (!image.empty())
{
case 103: //g
GROUPING_ALGORITHM = (GROUPING_ALGORITHM+1)%2;
cout << "Grouping switched to " << grouping_algorithms_str[GROUPING_ALGORITHM] << endl;
break;
case 111: //o
RECOGNITION = (RECOGNITION+1)%2;
cout << "OCR switched to " << recognitions_str[RECOGNITION] << endl;
break;
case 114: //r
REGION_TYPE = (REGION_TYPE+1)%2;
cout << "Regions switched to " << region_types_str[REGION_TYPE] << endl;
break;
case 115: //s
downsize = !downsize;
break;
default:
break;
frame = image.clone();
}
break;
default:
break;
}
}
return 0;
......@@ -389,11 +389,9 @@ bool isRepetitive(const string& s)
return true;
}
return false;
}
void er_draw(vector<Mat> &channels, vector<vector<ERStat> > &regions, vector<Vec2i> group, Mat& segmentation)
{
for (int r=0; r<(int)group.size(); r++)
......
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