I am using OpenCV for face and eye detection. To start with, I tested the sample program in OpenCV/Samples/c/facedetect.cpp. I gave two images as an input to this facedetect.exe - one is full and the other is cropped face of the same person. Now, the facedetect.cpp works fine with full image whereas it is not even detecting the face with the cropped image as input.
Although the cropped image contains only the face which is cropped using OpenCV face detector, In some bad cases I will get only mouth or lips or only part of the face. So my requirement here is to check both the eyes are there in an image or not.
The below are the two sample pictures one is full image where I get proper output:
The below is the image where I need to detect the eyes using facedetect.cpp:
So my question here is how to detect the eyes in the cropped image?
The below is the code of sample facedetect.cpp
#include "opencv2/objdetect/objdetect.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include <iostream>
#include <stdio.h>
using namespace std;
using namespace cv;
static void help()
{
cout << "\nThis program demonstrates the cascade recognizer. Now you can use Haar or LBP features.\n"
"This classifier can recognize many ~rigid objects, it's most known use is for faces.\n"
"Usage:\n"
"./facedetect [--cascade=<cascade_path> this is the primary trained classifier such as frontal face]\n"
" [--nested-cascade[=nested_cascade_path this an optional secondary classifier such as eyes]]\n"
" [--scale=<image scale greater or equal to 1, try 1.3 for example>\n"
" [filename|camera_index]\n\n"
"see facedetect.cmd for one call:\n"
"./facedetect --cascade=\"../../data/haarcascades/haarcascade_frontalface_alt.xml\" --nested-cascade=\"../../data/haarcascades/haarcascade_eye.xml\" --scale=1.3 \n"
"Hit any key to quit.\n"
"Using OpenCV version " << CV_VERSION << "\n" << endl;
}
void detectAndDraw( Mat& img,
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale);
String cascadeName = "../../data/haarcascades/haarcascade_frontalface_alt.xml";
String nestedCascadeName = "../../data/haarcascades/haarcascade_eye_tree_eyeglasses.xml";
int main( int argc, const char** argv )
{
CvCapture* capture = 0;
Mat frame, frameCopy, image;
const String scaleOpt = "--scale=";
size_t scaleOptLen = scaleOpt.length();
const String cascadeOpt = "--cascade=";
size_t cascadeOptLen = cascadeOpt.length();
const String nestedCascadeOpt = "--nested-cascade";
size_t nestedCascadeOptLen = nestedCascadeOpt.length();
String inputName;
help();
CascadeClassifier cascade, nestedCascade;
double scale = 1;
for( int i = 1; i < argc; i++ )
{
cout << "Processing " << i << " " << argv[i] << endl;
if( cascadeOpt.compare( 0, cascadeOptLen, argv[i], cascadeOptLen ) == 0 )
{
cascadeName.assign( argv[i] + cascadeOptLen );
cout << " from which we have cascadeName= " << cascadeName << endl;
}
else if( nestedCascadeOpt.compare( 0, nestedCascadeOptLen, argv[i], nestedCascadeOptLen ) == 0 )
{
if( argv[i][nestedCascadeOpt.length()] == '=' )
nestedCascadeName.assign( argv[i] + nestedCascadeOpt.length() + 1 );
if( !nestedCascade.load( nestedCascadeName ) )
cerr << "WARNING: Could not load classifier cascade for nested objects" << endl;
}
else if( scaleOpt.compare( 0, scaleOptLen, argv[i], scaleOptLen ) == 0 )
{
if( !sscanf( argv[i] + scaleOpt.length(), "%lf", &scale ) || scale < 1 )
scale = 1;
cout << " from which we read scale = " << scale << endl;
}
else if( argv[i][0] == '-' )
{
cerr << "WARNING: Unknown option %s" << argv[i] << endl;
}
else
inputName.assign( argv[i] );
}
if( !cascade.load( cascadeName ) )
{
cerr << "ERROR: Could not load classifier cascade" << endl;
cerr << "Usage: facedetect [--cascade=<cascade_path>]\n"
" [--nested-cascade[=nested_cascade_path]]\n"
" [--scale[=<image scale>\n"
" [filename|camera_index]\n" << endl ;
return -1;
}
if( inputName.empty() || (isdigit(inputName.c_str()[0]) && inputName.c_str()[1] == '\0') )
{
capture = cvCaptureFromCAM( inputName.empty() ? 0 : inputName.c_str()[0] - '0' );
int c = inputName.empty() ? 0 : inputName.c_str()[0] - '0' ;
if(!capture) cout << "Capture from CAM " << c << " didn't work" << endl;
}
else if( inputName.size() )
{
image = imread( inputName, 1 );
if( image.empty() )
{
capture = cvCaptureFromAVI( inputName.c_str() );
if(!capture) cout << "Capture from AVI didn't work" << endl;
}
}
else
{
image = imread( "lena.jpg", 1 );
if(image.empty()) cout << "Couldn't read lena.jpg" << endl;
}
cvNamedWindow( "result", 1 );
if( capture )
{
cout << "In capture ..." << endl;
for(;;)
{
IplImage* iplImg = cvQueryFrame( capture );
frame = iplImg;
if( frame.empty() )
break;
if( iplImg->origin == IPL_ORIGIN_TL )
frame.copyTo( frameCopy );
else
flip( frame, frameCopy, 0 );
detectAndDraw( frameCopy, cascade, nestedCascade, scale );
if( waitKey( 10 ) >= 0 )
goto _cleanup_;
}
waitKey(0);
_cleanup_:
cvReleaseCapture( &capture );
}
else
{
cout << "In image read" << endl;
if( !image.empty() )
{
detectAndDraw( image, cascade, nestedCascade, scale );
waitKey(0);
}
else if( !inputName.empty() )
{
/* assume it is a text file containing the
list of the image filenames to be processed - one per line */
FILE* f = fopen( inputName.c_str(), "rt" );
if( f )
{
char buf[1000+1];
while( fgets( buf, 1000, f ) )
{
int len = (int)strlen(buf), c;
while( len > 0 && isspace(buf[len-1]) )
len--;
buf[len] = '\0';
cout << "file " << buf << endl;
image = imread( buf, 1 );
if( !image.empty() )
{
detectAndDraw( image, cascade, nestedCascade, scale );
c = waitKey(0);
if( c == 27 || c == 'q' || c == 'Q' )
break;
}
else
{
cerr << "Aw snap, couldn't read image " << buf << endl;
}
}
fclose(f);
}
}
}
cvDestroyWindow("result");
return 0;
}
void detectAndDraw( Mat& img,
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale)
{
int i = 0;
double t = 0;
vector<Rect> faces;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, CV_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
t = (double)cvGetTickCount() - t;
printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
vector<Rect> nestedObjects;
Point center;
Scalar color = colors[i%8];
int radius;
center.x = cvRound((r->x + r->width*0.5)*scale);
center.y = cvRound((r->y + r->height*0.5)*scale);
radius = cvRound((r->width + r->height)*0.25*scale);
circle( img, center, radius, color, 3, 8, 0 );
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
center.x = cvRound((r->x + nr->x + nr->width*0.5)*scale);
center.y = cvRound((r->y + nr->y + nr->height*0.5)*scale);
radius = cvRound((nr->width + nr->height)*0.25*scale);
circle( img, center, radius, color, 3, 8, 0 );
}
}
cv::imshow( "result", img );
}
The original example detects faces first by cascade.detectMultiScale, then finds eyes in the detected faces by nestedCascade.detectMultiScale.
If you only need to detect the eyes, just use nestedCascade.detectMultiScale on the full image.
If you have a detected face (frontal face) a rough positions of the left and right eye regions are then estimated using anthropometric relations as show below.
Change the cascade classifier name:
String cascadeName = "../../data/haarcascades/haarcascade_frontalface_alt.xml";
change this to
String cascadeName = "../../data/haarcascades/haarcascade_eye_tree_eyeglasses.xml";
and pass the location of the image as the argument.
Related
I'm running into a problem, trying to perform a template matching using OpenCV on Ubuntu 18.04LTS
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include <iostream>
#include <stdio.h>
using namespace std;
using namespace cv;
int main( int argc, char** argv )
{
int match_method =5;
string image_window = "Source Image";
string result_window = "Result window";
Mat img, templ, result;
/// Load image and template
img = imread("./RI2.jpg", IMREAD_GRAYSCALE );
templ = imread("./Pump2.jpg", IMREAD_GRAYSCALE );
/// Create windows
//namedWindow( image_window, WINDOW_AUTOSIZE );
//namedWindow( result_window, WINDOW_AUTOSIZE );
/// Source image to display
Mat img_display;
img.copyTo( img_display );
/// Create the result matrix
int result_cols = img.cols - templ.cols + 1;
int result_rows = img.rows - templ.rows + 1;
result.create( result_rows, result_cols, CV_32FC1 );
/// Do the Matching and Normalize
matchTemplate( img, templ, result, match_method );
normalize( result, result, 0, 1, NORM_MINMAX, -1, Mat() );
Mat resultgrey(result_rows, result_cols, CV_8UC1);
cout << "resultgrey.size().width: " << resultgrey.size().width << endl;
cout << "resultgrey.size().height: " << resultgrey.size().height << endl;
cout << "result.size().width: " << result.size().width << endl;
cout << "result.size().height: " << result.size().height << endl;
if( match_method == 0 || match_method == 1 )
{
for (int i=0; i<result.size().width; i++)
{
for (int j=0; j<result.size().height; j++)
{
if (result.at<float>(i,j)>=0.1)
{
resultgrey.at<int>(i,j)=0;
}
else
{
resultgrey.at<int>(i,j)=1;
}
}
}
}
else
{
for (int i=0; i<result.size().width; i++)
{
for (int j=0; j<result.size().height; j++)
{
if (result.at<float>(i,j)<=0.98)
{
resultgrey.at<int>(i,j)=0;
//cout << "0" << endl;
}
else
{
resultgrey.at<int>(i,j)=1;
//cout << "1" << endl;
}
}
}
}
cout << "3" << endl;
/// Localizing the objects
vector<Point> matchLoclist;
//cout << resultgrey << endl;
findNonZero(resultgrey, matchLoclist);
cout << "4" << endl;
if (matchLoclist.size() == 0)
{
cout << "no matches found" << endl;
return 0;
}
///Draw Rectangles on Pumps found in the scene
for (int i=0; i<matchLoclist.size(); i++)
{
//cout << "matchLoclist[i].x: "<<matchLoclist[i].x << endl << "matchLoclist[i].y: " << matchLoclist[i].y << endl;
rectangle( img_display, matchLoclist[i], Point( matchLoclist[i].x + templ.cols, matchLoclist[i].y + templ.rows ), Scalar::all(0), 2, 8, 0 );
rectangle( result, matchLoclist[i], Point( matchLoclist[i].x + templ.cols, matchLoclist[i].y + templ.rows ), Scalar::all(0), 2, 8, 0 );
}
imshow( image_window, img_display );
imshow( result_window, result );
waitKey(0);
return 0;
}
as an output i get:
xxx#ubuntu:~/Projects/Template_matching$ ./template_matching
resultgrey.size().width: 1216
resultgrey.size().height: 723
result.size().width: 1216
result.size().height: 723
Segmentation fault (core dumped)
This happens during the double for-loop where either a 1 or a 0 gets written into "resultrgrey" as I never get the "3" as an output from the cout below
if I take different input pictures (espacially smaller ones) the programm tends to run without this error.
I appreciate any help or suggestions!
Alex
You write outside of the allocated buffer because of (1) incorrectly specified data types and (2) swapped arguments to .at, as #rafix07 has noted.
You create 8-bit matrix (8 in CV_8UC1):
Mat resultgrey(result_rows, result_cols, CV_8UC1);
but try to assign 32-bit values to its elements in double-for loop:
resultgrey.at<int>(i,j)=0;
Template method cv::Mat::at calculates address of the (i,j)-th element in memory, based on:
data type, specified in template instantiation,
pointer to data start, stored in the cv::Mat instance,
and data stride (distance in bytes between leftmost pixels of two consecutive lines), also stored in the cv::Mat instance.
Then it returns reference to it. No checks is performed, for speed, therefore it's your responsibility to submit correct arguments.
Size of int is 32 bits on most modern platforms, but can be differrent.
Generally, it is safer to use types from stdint.h header, that have explicit length and sign in their names: uint8_t, int32_t, etc
Look at reference about Mat::at method
const _Tp& cv::Mat::at ( int i0, int i1 ) const
Parameters
i0 Index along the dimension 0
i1 Index along the dimension 1
the first dimenstion is number of rows, the second dim is number of columns, so you should change all lines in your code with at
resultgrey.at<int>(i,j) // i means col, j means row
to
resultgrey.at<int>(j,i)
I am working on a queue bypass detection project and i need to select a region of interest or the boundary. If a person crosses the boundary, we should get an alert. Please help me to select a region of interest in live video similar to the one in the image.
please see this image
After doing some research I found what you need on github
#include "opencv2/opencv.hpp"
#include <iostream>
using namespace cv;
using namespace std;
/*~~~~~~~~~~~~~~~~~~*/
char ky;
bool got_roi = false;
Point points_array[4];
Mat src, ROI_Img,backup,ROI_MASK;
Rect2d ROI_Select;
int width_roi = 0, height_roi = 0,min_x,min_y,max_x,max_y;
Rect ROI_RECT ;
vector< vector<Point> > co_ordinates;
/*~~~~~~~~~~~~~~~~~~*/
/*~~~~~~~~~~~~~~~~~~*/
//Callback for mousclick event, the x-y coordinate of mouse button-down
//are stored array of points [points_array].
void mouse_click(int event, int x, int y, int flags, void *param)
{
static int count=0;
switch (event)
{
case CV_EVENT_LBUTTONDOWN:
{
switch (count) // number of set Point
{
case 0:
cout << "Select top-right point" << endl;
break;
case 1:
cout << "Select bottom-right point" << endl;
break;
case 2:
cout << "Select bottom-left point" << endl << endl;
break;
default:
break;
}
if (!got_roi) // you are not select ROI yet!
{
points_array[count] = Point(x,y);
circle(src, points_array[count], 2, Scalar(0, 255, 0), 2); //show points on image
imshow("My_Win", src);
count++;
if (count == 4) // if select 4 point finished
{
cout << "ROI x & y points :" << endl;
cout << points_array[0] << endl;
cout << points_array[1] << endl;
cout << points_array[2] << endl;
cout << points_array[3] << endl;
cout << endl << "ROI Saved You can continue with double press any keys except 'c' " << endl <<"once press 'c' or 'C' to clear points and retry select ROI " << endl << endl;
ky = waitKey(0) & 0xFF;
if (ky == 99 || ky == 67) // c or C to clear
{
backup.copyTo(src);
points_array[0] = Point(0, 0);
points_array[1] = Point(0, 0);
points_array[2] = Point(0, 0);
points_array[3] = Point(0, 0);
imshow("My_Win", src);
count = 0;
cout << endl << endl << endl << "#--------------------- Clear Points! ------------------# " << endl << endl << endl ;
}
else // user accept points & dosn't want to clear them
{
min_x = std::min(points_array[0].x, points_array[3].x); //find rectangle for minimum ROI surround it!
max_x = std::max(points_array[1].x, points_array[2].x);
min_y = std::min(points_array[0].y, points_array[1].y);
max_y = std::max(points_array[3].y, points_array[2].y);
height_roi = max_y - min_y;
width_roi = max_x - min_x;
ROI_RECT = Rect(min_x, min_y, width_roi, height_roi);
got_roi = true;
co_ordinates.push_back(vector<Point>());
co_ordinates[0].push_back(points_array[0]);
co_ordinates[0].push_back(points_array[1]);
co_ordinates[0].push_back(points_array[2]);
co_ordinates[0].push_back(points_array[3]);
}
}
}
else { // if got_roi se true => select roi before
cout << endl << "You Select ROI Before " << endl << "if you want to clear point press 'c' or double press other keys to continue" << endl << endl;
}
break;
}
}
}
/*~~~~~~~~~~~~~~~~~~*/
int main()
{
// replace all "My_Win" with your window name
/*~~~~~~~~~~~~~~~~~~*/
namedWindow("My_Win", 1);
/*~~~~~~~~~~~~~~~~~~*/
VideoCapture input_video("Video_path");
// Set source imafe as [src]
/*~~~~~~~~~~~~~~~~~~*/
input_video >> src;
imshow("My_Win", src);
src.copyTo(backup);
setMouseCallback("My_Win", mouse_click, 0);
waitKey(0);
Mat mask(src.rows, src.cols, CV_8UC1, cv::Scalar(0));
drawContours(mask, co_ordinates, 0, Scalar(255), CV_FILLED, 8);
/*~~~~~~~~~~~~~~~~~~*/
while (1)
{
input_video >> src;
/*~~~~~~~~~~~~~~~~~~*/
//Need to copy Select ROI as MASK
src.copyTo(ROI_MASK, mask);
//Creat a rectangle around the Mask to reduce size of mask
ROI_Img = ROI_MASK(ROI_RECT);
/*~~~~~~~~~~~~~~~~~~*/
//Show Image
imshow("My_Win", ROI_Img);
// Do remaining processing here on capture roi for every frame
if(char (waitKey(1)& 0xFF) == 27) break;
}
}
I am doing a project for which I need to detect the rear of a car using HOG features. Once I calculated the HOG features I trained the cvsvm using positive and negative samples. cvsvm is correctly classifying the new data. Here is my code that I used to train cvsvm.
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/ml/ml.hpp>
#include "opencv2/opencv.hpp"
#include "LinearSVM.h"
using namespace cv;
using namespace std;
int main(void)
{
LinearSVM *s = new LinearSVM;
vector<float> values, values1, values2, values3, values4;
FileStorage fs2("/home/ubuntu/Desktop/opencv-svm/vecSupport.yml", FileStorage::READ);
FileStorage fs3("/home/ubuntu/Desktop/opencv-svm/vecSupport1.yml", FileStorage::READ);
FileStorage fs4("/home/ubuntu/Desktop/opencv-svm/vecSupport2.yml", FileStorage::READ);
FileStorage fs5("/home/ubuntu/Desktop/opencv-svm/vecSupport3.yml", FileStorage::READ);
FileStorage fs6("/home/ubuntu/Desktop/opencv-svm/vecSupport4.yml", FileStorage::READ);
fs2["vector"]>>values;
fs3["vector"]>>values1;
fs4["vector"]>>values2;
fs5["vector"]>>values3;
fs6["vector"]>>values4;
//fill with data
values.insert(values.end(), values1.begin(), values1.end());
values.insert(values.end(), values2.begin(), values2.end());
fs2.release();
fs3.release();
fs4.release();
float arr[188496];
float car[2772];
float noncar[2772];
// move positive and negative to arr
std::copy(values.begin(), values.end(), arr);
std::copy(values3.begin(), values3.end(), car);
std::copy(values4.begin(), values4.end(), noncar);
float labels[68];
for (unsigned int s = 0; s < 68; s++)
{
if (s<34)
labels[s] = +1;
else
labels[s] = -1;
}
Mat labelsMat(68, 1, CV_32FC1, labels);
Mat trainingDataMat(68,2772, CV_32FC1, arr);
// Set up SVM's parameters
CvSVMParams params;
params.svm_type = CvSVM::C_SVC;
params.kernel_type = CvSVM::LINEAR;
params.term_crit = cvTermCriteria(CV_TERMCRIT_ITER, 100, 1e-6);
// Train the SVM
LinearSVM SVM;
SVM.train(trainingDataMat, labelsMat, Mat(), Mat(), params);
Mat matinput(1,2772,CV_32FC1,noncar);
//cout<<matinput;
float response = SVM.predict(matinput);
cout<<"Response : "<<response<<endl;
SVM.save("Classifier.xml");
vector<float>primal;
// LinearSVM s;
//s.getSupportVector(primal);
SVM.getSupportVector(primal);
FileStorage fs("/home/ubuntu/Desktop/opencv-svm/test.yml", FileStorage::WRITE);
fs << "dector" << primal;
fs.release();
}
// LinearSVM cpp file
#include "LinearSVM.h"
void LinearSVM::getSupportVector(std::vector<float>& support_vector) const {
int sv_count = get_support_vector_count();
const CvSVMDecisionFunc* df = decision_func;
const double* alphas = df[0].alpha;
double rho = df[0].rho;
int var_count = get_var_count();
support_vector.resize(var_count, 0);
for (unsigned int r = 0; r < (unsigned)sv_count; r++) {
float myalpha = alphas[r];
const float* v = get_support_vector(r);
for (int j = 0; j < var_count; j++,v++) {
support_vector[j] += (-myalpha) * (*v);
}
}
support_vector.push_back(rho);
}
// LinearSVM head file
#ifndef LINEAR_SVM_H_
#define LINEAR_SVM_H_
#include <opencv2/core/core.hpp>
#include <opencv2/ml/ml.hpp>
class LinearSVM: public CvSVM {
public:
void getSupportVector(std::vector<float>& support_vector) const;
};
#endif /* LINEAR_SVM_H_ */
After this step I got the vector file that I can fed into setsvmdetector method. Here is my code. I have used window size of 96 x 64 and scale of 1.11
#include <iostream>
#include <fstream>
#include <string>
#include <time.h>
#include <iostream>
#include <sstream>
#include <iomanip>
#include <stdexcept>
#include <stdexcept>
#include "opencv2/gpu/gpu.hpp"
#include "opencv2/highgui/highgui.hpp"
using namespace std;
using namespace cv;
bool help_showed = false;
class Args
{
public:
Args();
static Args read(int argc, char** argv);
string src;
bool src_is_video;
bool src_is_camera;
int camera_id;
bool write_video;
string dst_video;
double dst_video_fps;
bool make_gray;
bool resize_src;
int width, height;
double scale;
int nlevels;
int gr_threshold;
double hit_threshold;
bool hit_threshold_auto;
int win_width;
int win_stride_width, win_stride_height;
bool gamma_corr;
};
class App
{
public:
App(const Args& s);
void run();
void handleKey(char key);
void hogWorkBegin();
void hogWorkEnd();
string hogWorkFps() const;
void workBegin();
void workEnd();
string workFps() const;
string message() const;
private:
App operator=(App&);
Args args;
bool running;
bool use_gpu;
bool make_gray;
double scale;
int gr_threshold;
int nlevels;
double hit_threshold;
bool gamma_corr;
int64 hog_work_begin;
double hog_work_fps;
int64 work_begin;
double work_fps;
};
static void printHelp()
{
cout << "Histogram of Oriented Gradients descriptor and detector sample.\n"
<< "\nUsage: hog_gpu\n"
<< " (<image>|--video <vide>|--camera <camera_id>) # frames source\n"
<< " [--make_gray <true/false>] # convert image to gray one or not\n"
<< " [--resize_src <true/false>] # do resize of the source image or not\n"
<< " [--width <int>] # resized image width\n"
<< " [--height <int>] # resized image height\n"
<< " [--hit_threshold <double>] # classifying plane distance threshold (0.0 usually)\n"
<< " [--scale <double>] # HOG window scale factor\n"
<< " [--nlevels <int>] # max number of HOG window scales\n"
<< " [--win_width <int>] # width of the window (48 or 64)\n"
<< " [--win_stride_width <int>] # distance by OX axis between neighbour wins\n"
<< " [--win_stride_height <int>] # distance by OY axis between neighbour wins\n"
<< " [--gr_threshold <int>] # merging similar rects constant\n"
<< " [--gamma_correct <int>] # do gamma correction or not\n"
<< " [--write_video <bool>] # write video or not\n"
<< " [--dst_video <path>] # output video path\n"
<< " [--dst_video_fps <double>] # output video fps\n";
help_showed = true;
}
int main(int argc, char** argv)
{
try
{
if (argc < 2)
printHelp();
Args args = Args::read(argc, argv);
if (help_showed)
return -1;
App app(args);
app.run();
}
catch (const Exception& e) { return cout << "error: " << e.what() << endl, 1; }
catch (const exception& e) { return cout << "error: " << e.what() << endl, 1; }
catch(...) { return cout << "unknown exception" << endl, 1; }
return 0;
}
Args::Args()
{
src_is_video = false;
src_is_camera = false;
camera_id = 0;
write_video = false;
dst_video_fps = 24.;
make_gray = false;
resize_src = false;
width = 640;
height = 480;
scale = 1.11;
nlevels = 13;
gr_threshold = 1;
hit_threshold = 1.4;
hit_threshold_auto = true;
win_width = 64;
win_stride_width = 8;
win_stride_height = 8;
gamma_corr = true;
}
Args Args::read(int argc, char** argv)
{
Args args;
for (int i = 1; i < argc; i++)
{
if (string(argv[i]) == "--make_gray") args.make_gray = (string(argv[++i]) == "true");
else if (string(argv[i]) == "--resize_src") args.resize_src = (string(argv[++i]) == "true");
else if (string(argv[i]) == "--width") args.width = atoi(argv[++i]);
else if (string(argv[i]) == "--height") args.height = atoi(argv[++i]);
else if (string(argv[i]) == "--hit_threshold")
{
args.hit_threshold = atof(argv[++i]);
args.hit_threshold_auto = false;
}
else if (string(argv[i]) == "--scale") args.scale = atof(argv[++i]);
else if (string(argv[i]) == "--nlevels") args.nlevels = atoi(argv[++i]);
else if (string(argv[i]) == "--win_width") args.win_width = atoi(argv[++i]);
else if (string(argv[i]) == "--win_stride_width") args.win_stride_width = atoi(argv[++i]);
else if (string(argv[i]) == "--win_stride_height") args.win_stride_height = atoi(argv[++i]);
else if (string(argv[i]) == "--gr_threshold") args.gr_threshold = atoi(argv[++i]);
else if (string(argv[i]) == "--gamma_correct") args.gamma_corr = (string(argv[++i]) == "true");
else if (string(argv[i]) == "--write_video") args.write_video = (string(argv[++i]) == "true");
else if (string(argv[i]) == "--dst_video") args.dst_video = argv[++i];
else if (string(argv[i]) == "--dst_video_fps") args.dst_video_fps = atof(argv[++i]);
else if (string(argv[i]) == "--help") printHelp();
else if (string(argv[i]) == "--video") { args.src = argv[++i]; args.src_is_video = true; }
else if (string(argv[i]) == "--camera") { args.camera_id = atoi(argv[++i]); args.src_is_camera = true; }
else if (args.src.empty()) args.src = argv[i];
else throw runtime_error((string("unknown key: ") + argv[i]));
}
return args;
}
App::App(const Args& s)
{
cv::gpu::printShortCudaDeviceInfo(cv::gpu::getDevice());
args = s;
cout << "\nControls:\n"
<< "\tESC - exit\n"
<< "\tm - change mode GPU <-> CPU\n"
<< "\tg - convert image to gray or not\n"
<< "\t1/q - increase/decrease HOG scale\n"
<< "\t2/w - increase/decrease levels count\n"
<< "\t3/e - increase/decrease HOG group threshold\n"
<< "\t4/r - increase/decrease hit threshold\n"
<< endl;
use_gpu = true;
make_gray = args.make_gray;
scale = args.scale;
gr_threshold = args.gr_threshold;
nlevels = args.nlevels;
if (args.hit_threshold_auto)
args.hit_threshold = args.win_width == 48 ? 1.4 : 0.;
hit_threshold = args.hit_threshold;
gamma_corr = args.gamma_corr;
/*
if (args.win_width != 64 && args.win_width != 48)
args.win_width = 64;*/
cout << "Scale: " << scale << endl;
if (args.resize_src)
cout << "Resized source: (" << args.width << ", " << args.height << ")\n";
cout << "Group threshold: " << gr_threshold << endl;
cout << "Levels number: " << nlevels << endl;
cout << "Win width: " << args.win_width << endl;
cout << "Win stride: (" << args.win_stride_width << ", " << args.win_stride_height << ")\n";
cout << "Hit threshold: " << hit_threshold << endl;
cout << "Gamma correction: " << gamma_corr << endl;
cout << endl;
}
void App::run()
{
FileStorage fs("/home/ubuntu/Desktop/implemenatation/vecSupport.yml", FileStorage::READ);
vector<float> detector;
int frameCount;
fs["vector"] >> detector;
for (unsigned int i=0; i<detector.size(); i++)
{
std::cout << std::fixed << std::setprecision(10) << detector[i] << std::endl;
}
fs.release();
running = true;
cv::VideoWriter video_writer;
Size win_size(96,64); //(64, 128) or (48, 96)
Size win_stride(args.win_stride_width, args.win_stride_height);
// Create HOG descriptors and detectors here
/*
vector<float> detector;
if (win_size == Size(64, 128))
detector = cv::gpu::HOGDescriptor::getPeopleDetector64x128();
else
detector = cv::gpu::HOGDescriptor::getPeopleDetector48x96();*/
cv::gpu::HOGDescriptor gpu_hog(win_size, Size(16, 16), Size(8, 8), Size(8, 8), 9,
cv::gpu::HOGDescriptor::DEFAULT_WIN_SIGMA, 0.2, gamma_corr,
cv::gpu::HOGDescriptor::DEFAULT_NLEVELS);
cv::HOGDescriptor cpu_hog(win_size, Size(16, 16), Size(8, 8), Size(8, 8), 9, 1, -1,
HOGDescriptor::L2Hys, 0.2, gamma_corr, cv::HOGDescriptor::DEFAULT_NLEVELS);
gpu_hog.setSVMDetector(detector);
cpu_hog.setSVMDetector(detector);
while (running)
{
VideoCapture vc;
Mat frame;
if (args.src_is_video)
{
vc.open(args.src.c_str());
if (!vc.isOpened())
throw runtime_error(string("can't open video file: " + args.src));
vc >> frame;
}
else if (args.src_is_camera)
{
vc.open(args.camera_id);
if (!vc.isOpened())
{
stringstream msg;
msg << "can't open camera: " << args.camera_id;
throw runtime_error(msg.str());
}
vc >> frame;
}
else
{
frame = imread(args.src);
if (frame.empty())
throw runtime_error(string("can't open image file: " + args.src));
}
Mat img_aux, img, img_to_show;
gpu::GpuMat gpu_img;
// Iterate over all frames
while (running && !frame.empty())
{
workBegin();
// Change format of the image
if (make_gray) cvtColor(frame, img_aux, CV_BGR2GRAY);
else if (use_gpu) cvtColor(frame, img_aux, CV_BGR2BGRA);
else frame.copyTo(img_aux);
// Resize image
if (args.resize_src) resize(img_aux, img, Size(args.width, args.height));
else img = img_aux;
img_to_show = img;
gpu_hog.nlevels = nlevels;
cpu_hog.nlevels = nlevels;
vector<Rect> found;
// Perform HOG classification
hogWorkBegin();
if (use_gpu)
{
gpu_img.upload(img);
gpu_hog.detectMultiScale(gpu_img, found, hit_threshold, win_stride,
Size(0, 0), scale, gr_threshold);
}
else cpu_hog.detectMultiScale(img, found, hit_threshold, win_stride,
Size(0, 0), scale, gr_threshold);
hogWorkEnd();
// Draw positive classified windows
for (size_t i = 0; i < found.size(); i++)
{
Rect r = found[i];
rectangle(img_to_show, r.tl(), r.br(), CV_RGB(0, 255, 0), 3);
}
if (use_gpu)
putText(img_to_show, "Mode: GPU", Point(5, 25), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
else
putText(img_to_show, "Mode: CPU", Point(5, 25), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
putText(img_to_show, "FPS (HOG only): " + hogWorkFps(), Point(5, 65), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
putText(img_to_show, "FPS (total): " + workFps(), Point(5, 105), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
imshow("opencv_gpu_hog", img_to_show);
if (args.src_is_video || args.src_is_camera) vc >> frame;
workEnd();
if (args.write_video)
{
if (!video_writer.isOpened())
{
video_writer.open(args.dst_video, CV_FOURCC('x','v','i','d'), args.dst_video_fps,
img_to_show.size(), true);
if (!video_writer.isOpened())
throw std::runtime_error("can't create video writer");
}
if (make_gray) cvtColor(img_to_show, img, CV_GRAY2BGR);
else cvtColor(img_to_show, img, CV_BGRA2BGR);
video_writer << img;
}
handleKey((char)waitKey(3));
}
}
}
void App::handleKey(char key)
{
switch (key)
{
case 27:
running = false;
break;
case 'm':
case 'M':
use_gpu = !use_gpu;
cout << "Switched to " << (use_gpu ? "CUDA" : "CPU") << " mode\n";
break;
case 'g':
case 'G':
make_gray = !make_gray;
cout << "Convert image to gray: " << (make_gray ? "YES" : "NO") << endl;
break;
case '1':
scale *= 1.11;
cout << "Scale: " << scale << endl;
break;
case 'q':
case 'Q':
scale /= 1.11;
cout << "Scale: " << scale << endl;
break;
case '2':
nlevels++;
cout << "Levels number: " << nlevels << endl;
break;
case 'w':
case 'W':
nlevels = max(nlevels - 1, 1);
cout << "Levels number: " << nlevels << endl;
break;
case '3':
gr_threshold++;
cout << "Group threshold: " << gr_threshold << endl;
break;
case 'e':
case 'E':
gr_threshold = max(0, gr_threshold - 1);
cout << "Group threshold: " << gr_threshold << endl;
break;
case '4':
hit_threshold+=0.25;
cout << "Hit threshold: " << hit_threshold << endl;
break;
case 'r':
case 'R':
hit_threshold = max(0.0, hit_threshold - 0.25);
cout << "Hit threshold: " << hit_threshold << endl;
break;
case 'c':
case 'C':
gamma_corr = !gamma_corr;
cout << "Gamma correction: " << gamma_corr << endl;
break;
}
}
inline void App::hogWorkBegin() { hog_work_begin = getTickCount(); }
inline void App::hogWorkEnd()
{
int64 delta = getTickCount() - hog_work_begin;
double freq = getTickFrequency();
hog_work_fps = freq / delta;
}
inline string App::hogWorkFps() const
{
stringstream ss;
ss << hog_work_fps;
return ss.str();
}
inline void App::workBegin() { work_begin = getTickCount(); }
inline void App::workEnd()
{
int64 delta = getTickCount() - work_begin;
double freq = getTickFrequency();
work_fps = freq / delta;
}
inline string App::workFps() const
{
stringstream ss;
ss << work_fps;
return ss.str();
}
Problem:
I am not able to detect anything. Can someone look at my work and can let me know what I am doing wrong. Any suggestions would be valuable. Thank you. From last four weeks I am doing these steps over and over again.
P.S: You can find yaml files here and test images along with the annotations here
First of all, partition your data for cross-validation as suggested already. Second thing is that it is a good idea to use RBF kernel rather than Linear kernel. I highly doubt that a linear kernel can learn complex objects. A brief explanation is given here. Finally, experiment with the parameters. To do that, you need to check the limits of the parameter space, it's been a while since I haven't used SVMs therefore I cannot provide any details but a grid search with 20% cross-validation is a good start.
I need to count the number of faces in a picture on the commandline (to be used in a bash script: do-something-if-picture-passed-contains-faces, else try next picture).
So far I have the facedetect OpenCV example working, but this example continuously displays the picture - all I'd need is a number returned (or, simply an errorcode: 0 if no face found, 1 if a face has been found).
Sadly my C++ skills are abysmal, could someone point me in the right direction?
I'd use python or ruby, but the bindings to OpenCV seem to be more then broken in Ubuntu 12.04, none of the examples work right (or at all).
Thank you!
Edit: The example I was talking about as installed by OpenCV under Ubuntu
cat /usr/share/doc/opencv-doc/examples/c/facedetect.cpp:
#include "opencv2/objdetect/objdetect.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include <iostream>
#include <stdio.h>
using namespace std;
using namespace cv;
void help()
{
cout << "\nThis program demonstrates the cascade recognizer. Now you can use Haar or LBP features.\n"
"This classifier can recognize many ~rigid objects, it's most known use is for faces.\n"
"Usage:\n"
"./facedetect [--cascade=<cascade_path> this is the primary trained classifier such as frontal face]\n"
" [--nested-cascade[=nested_cascade_path this an optional secondary classifier such as eyes]]\n"
" [--scale=<image scale greater or equal to 1, try 1.3 for example>\n"
" [filename|camera_index]\n\n"
"see facedetect.cmd for one call:\n"
"./facedetect --cascade=\"../../data/haarcascades/haarcascade_frontalface_alt.xml\" --nested-cascade=\"../../data/haarcascades/haarcascade_eye.xml\" --scale=1.3 \n"
"Hit any key to quit.\n"
"Using OpenCV version " << CV_VERSION << "\n" << endl;
}
void detectAndDraw( Mat& img,
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale);
String cascadeName = "../../data/haarcascades/haarcascade_frontalface_alt.xml";
String nestedCascadeName = "../../data/haarcascades/haarcascade_eye_tree_eyeglasses.xml";
int main( int argc, const char** argv )
{
CvCapture* capture = 0;
Mat frame, frameCopy, image;
const String scaleOpt = "--scale=";
size_t scaleOptLen = scaleOpt.length();
const String cascadeOpt = "--cascade=";
size_t cascadeOptLen = cascadeOpt.length();
const String nestedCascadeOpt = "--nested-cascade";
size_t nestedCascadeOptLen = nestedCascadeOpt.length();
String inputName;
help();
CascadeClassifier cascade, nestedCascade;
double scale = 1;
for( int i = 1; i < argc; i++ )
{
cout << "Processing " << i << " " << argv[i] << endl;
if( cascadeOpt.compare( 0, cascadeOptLen, argv[i], cascadeOptLen ) == 0 )
{
cascadeName.assign( argv[i] + cascadeOptLen );
cout << " from which we have cascadeName= " << cascadeName << endl;
}
else if( nestedCascadeOpt.compare( 0, nestedCascadeOptLen, argv[i], nestedCascadeOptLen ) == 0 )
{
if( argv[i][nestedCascadeOpt.length()] == '=' )
nestedCascadeName.assign( argv[i] + nestedCascadeOpt.length() + 1 );
if( !nestedCascade.load( nestedCascadeName ) )
cerr << "WARNING: Could not load classifier cascade for nested objects" << endl;
}
else if( scaleOpt.compare( 0, scaleOptLen, argv[i], scaleOptLen ) == 0 )
{
if( !sscanf( argv[i] + scaleOpt.length(), "%lf", &scale ) || scale < 1 )
scale = 1;
cout << " from which we read scale = " << scale << endl;
}
else if( argv[i][0] == '-' )
{
cerr << "WARNING: Unknown option %s" << argv[i] << endl;
}
else
inputName.assign( argv[i] );
}
if( !cascade.load( cascadeName ) )
{
cerr << "ERROR: Could not load classifier cascade" << endl;
cerr << "Usage: facedetect [--cascade=<cascade_path>]\n"
" [--nested-cascade[=nested_cascade_path]]\n"
" [--scale[=<image scale>\n"
" [filename|camera_index]\n" << endl ;
return -1;
}
if( inputName.empty() || (isdigit(inputName.c_str()[0]) && inputName.c_str()[1] == '\0') )
{
capture = cvCaptureFromCAM( inputName.empty() ? 0 : inputName.c_str()[0] - '0' );
int c = inputName.empty() ? 0 : inputName.c_str()[0] - '0' ;
if(!capture) cout << "Capture from CAM " << c << " didn't work" << endl;
}
else if( inputName.size() )
{
image = imread( inputName, 1 );
if( image.empty() )
{
capture = cvCaptureFromAVI( inputName.c_str() );
if(!capture) cout << "Capture from AVI didn't work" << endl;
}
}
else
{
image = imread( "lena.jpg", 1 );
if(image.empty()) cout << "Couldn't read lena.jpg" << endl;
}
cvNamedWindow( "result", 1 );
if( capture )
{
cout << "In capture ..." << endl;
for(;;)
{
IplImage* iplImg = cvQueryFrame( capture );
frame = iplImg;
if( frame.empty() )
break;
if( iplImg->origin == IPL_ORIGIN_TL )
frame.copyTo( frameCopy );
else
flip( frame, frameCopy, 0 );
detectAndDraw( frameCopy, cascade, nestedCascade, scale );
if( waitKey( 10 ) >= 0 )
goto _cleanup_;
}
waitKey(0);
_cleanup_:
cvReleaseCapture( &capture );
}
else
{
cout << "In image read" << endl;
if( !image.empty() )
{
detectAndDraw( image, cascade, nestedCascade, scale );
waitKey(0);
}
else if( !inputName.empty() )
{
/* assume it is a text file containing the
list of the image filenames to be processed - one per line */
FILE* f = fopen( inputName.c_str(), "rt" );
if( f )
{
char buf[1000+1];
while( fgets( buf, 1000, f ) )
{
int len = (int)strlen(buf), c;
while( len > 0 && isspace(buf[len-1]) )
len--;
buf[len] = '\0';
cout << "file " << buf << endl;
image = imread( buf, 1 );
if( !image.empty() )
{
detectAndDraw( image, cascade, nestedCascade, scale );
c = waitKey(0);
if( c == 27 || c == 'q' || c == 'Q' )
break;
}
else
{
cerr << "Aw snap, couldn't read image " << buf << endl;
}
}
fclose(f);
}
}
}
cvDestroyWindow("result");
return 0;
}
void detectAndDraw( Mat& img,
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale)
{
int i = 0;
double t = 0;
vector<Rect> faces;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, CV_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
t = (double)cvGetTickCount() - t;
printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
vector<Rect> nestedObjects;
Point center;
Scalar color = colors[i%8];
int radius;
center.x = cvRound((r->x + r->width*0.5)*scale);
center.y = cvRound((r->y + r->height*0.5)*scale);
radius = cvRound((r->width + r->height)*0.25*scale);
circle( img, center, radius, color, 3, 8, 0 );
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
center.x = cvRound((r->x + nr->x + nr->width*0.5)*scale);
center.y = cvRound((r->y + nr->y + nr->height*0.5)*scale);
radius = cvRound((nr->width + nr->height)*0.25*scale);
circle( img, center, radius, color, 3, 8, 0 );
}
}
cv::imshow( "result", img );
}
Change the void detectAndDraw to int detectAndDraw
The int detectAndDraw will return faces.end()-faces.begin();
and you will get the number of faces in a picture. hope this will help
I try to run facedetect opencv sample with vs2010.
debug result "Unhandled exception at 0x53fa42bf in facedetect.exe: 0xC0000005: Access violation writing location 0x00000000."
Here is the code
txt file: http://ebooks-libs.com/backup/facedetect-opencv2.1.txt
cpp file: http://ebooks-libs.com/backup/facedetect.cpp
#include "stdafx.h"
#include <iostream>
#include <cstdio>
#define CV_NO_BACKWARD_COMPATIBILITY
#include "cv.h"
#include "highgui.h"
#ifdef _EiC
#define WIN32
#endif
using namespace std;
using namespace cv;
void detectAndDraw( Mat& img,
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale);
String cascadeName ="./data/haarcascades/haarcascade_frontalface_alt.xml";
String nestedCascadeName ="./data/haarcascades/haarcascade_eye_tree_eyeglasses.xml";
int main( int argc, const char** argv )
{
CvCapture* capture = 0;
Mat frame, frameCopy, image;
const String scaleOpt = "--scale=";
size_t scaleOptLen = scaleOpt.length();
const String cascadeOpt = "--cascade=";
size_t cascadeOptLen = cascadeOpt.length();
const String nestedCascadeOpt = "--nested-cascade";
size_t nestedCascadeOptLen = nestedCascadeOpt.length();
String inputName;
CascadeClassifier cascade, nestedCascade;
double scale = 1;
for( int i = 1; i < argc; i++ )
{
if( cascadeOpt.compare( 0, cascadeOptLen, argv[i], cascadeOptLen ) == 0 )
cascadeName.assign( argv[i] + cascadeOptLen );
else if( nestedCascadeOpt.compare( 0, nestedCascadeOptLen, argv[i], nestedCascadeOptLen ) == 0 )
{
if( argv[i][nestedCascadeOpt.length()] == '=' )
nestedCascadeName.assign( argv[i] + nestedCascadeOpt.length() + 1 );
if( !nestedCascade.load( nestedCascadeName ) )
cerr << "WARNING: Could not load classifier cascade for nested objects" << endl;
}
else if( scaleOpt.compare( 0, scaleOptLen, argv[i], scaleOptLen ) == 0 )
{
if( !sscanf( argv[i] + scaleOpt.length(), "%lf", &scale ) || scale < 1 )
scale = 1;
}
else if( argv[i][0] == '-' )
{
cerr << "WARNING: Unknown option %s" << argv[i] << endl;
}
else
inputName.assign( argv[i] );
}
if( !cascade.load( cascadeName ) )
{
cerr << "ERROR: Could not load classifier cascade" << endl;
cerr << "Usage: facedetect [--cascade=\"<cascade_path>\"]\n"
" [--nested-cascade[=\"nested_cascade_path\"]]\n"
" [--scale[=<image scale>\n"
" [filename|camera_index]\n" ;
return -1;
}
if( inputName.empty() || (isdigit(inputName.c_str()[0]) && inputName.c_str()[1] == '\0') )
capture = cvCaptureFromCAM( inputName.empty() ? 0 : inputName.c_str()[0] - '0' );
else if( inputName.size() )
{
image = imread( inputName, 1 );
if( image.empty() )
capture = cvCaptureFromAVI( inputName.c_str() );
}
else
image = imread( "lena.jpg", 1 );
cvNamedWindow( "result", 1 );
if( capture )
{
for(;;)
{
IplImage* iplImg = cvQueryFrame( capture );
frame = iplImg;
if( frame.empty() )
break;
if( iplImg->origin == IPL_ORIGIN_TL )
frame.copyTo( frameCopy );
else
flip( frame, frameCopy, 0 );
detectAndDraw( frameCopy, cascade, nestedCascade, scale );
if( waitKey( 10 ) >= 0 )
goto _cleanup_;
}
waitKey(0);
_cleanup_:
cvReleaseCapture( &capture );
}
else
{
if( !image.empty() )
{
detectAndDraw( image, cascade, nestedCascade, scale );
waitKey(0);
}
else if( !inputName.empty() )
{
/* assume it is a text file containing the
list of the image filenames to be processed - one per line */
FILE* f = fopen( inputName.c_str(), "rt" );
if( f )
{
char buf[1000+1];
while( fgets( buf, 1000, f ) )
{
int len = (int)strlen(buf), c;
while( len > 0 && isspace(buf[len-1]) )
len--;
buf[len] = '\0';
cout << "file " << buf << endl;
image = imread( buf, 1 );
if( !image.empty() )
{
detectAndDraw( image, cascade, nestedCascade, scale );
c = waitKey(0);
if( c == 27 || c == 'q' || c == 'Q' )
break;
}
}
fclose(f);
}
}
}
cvDestroyWindow("result");
return 0;
}
void detectAndDraw( Mat& img,
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale)
{
int i = 0;
double t = 0;
vector<Rect> faces;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, CV_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,1.1, 2, 0 |CV_HAAR_SCALE_IMAGE,Size(30, 30) );
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
t = (double)cvGetTickCount() - t;
printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
vector<Rect> nestedObjects;
Point center;
Scalar color = colors[i%8];
int radius;
center.x = cvRound((r->x + r->width*0.5)*scale);
center.y = cvRound((r->y + r->height*0.5)*scale);
radius = cvRound((r->width + r->height)*0.25*scale);
circle( img, center, radius, color, 3, 8, 0 );
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
center.x = cvRound((r->x + nr->x + nr->width*0.5)*scale);
center.y = cvRound((r->y + nr->y + nr->height*0.5)*scale);
radius = cvRound((nr->width + nr->height)*0.25*scale);
circle( img, center, radius, color, 3, 8, 0 );
}
}
cv::imshow( "result", img );
}
Need some help how to resolve it...
The access violation error probably means you are accessing a pointer that you haven't set the value for.
If you don't understand how to use the debugger (learn!) put printf("ok1,2,3 ....\n"); liberally through the code and work out how far it's gettign so you can narrow down where the error happens
I got this error too with OpenCV 2.3 on VS2010, even after adjusting the code so that cascadeName uses the full path to haarcascade_frontalface_alt.xml.
I was able to pinpoint the problem to the line that crashes the application:
if( !cascade.load( cascadeName ) )
The crash is coming from OpenCV's code and I don't know why it happens.