I'm using the cascade classifier with the front-face training data to detect faces in a still image (i.e. static jpg). I don't want to have to search the whole image for faces at once, so I send the cascade classifier an ROI from the full image. What I've found is that the classifier's ability to find the face in the image is dependent on the dimensions/position of the ROI I give it. Note, I only give it ROIs that include the face fully, and with lots of margin.
I'm using OpenCV 3.0.0.
I have had modified the OpenCV sample program to demonstrate the behavior behavior, but was then informed that that sample program was old and used an interface to the cascade classifier that is no longer valid. I started to test the new example code (obtained from: http://docs.opencv.org/master/db/d28/tutorial_cascade_classifier.html#gsc.tab=0) but that code can't find the face in my sample image at all (see attachment). If you search for "** Mod begin" you can find the places below), which is the same image I edited. have been using all along. I've also found that when I did not change anything fundamental about how the example test some other images, the sample program runs, I just introduced an ROI for the search and automated it to step through a bunch of different ROI heights. A message will print on the console for ROIs where no face could be detected. If you build this program you can see in the output window that the location/size of the detected face changes a little as the ROI's height changes.seg faults.
Sample image: C:\fakepath\faceDetectTestImage.png
Code embedded (apologies for the size of the code "block" but Here is the modified objectDetection.cpp code, with my minor mods marked. All I don't know did was make it so that you can use a better way to post it).
I believe this might indicate a bug in the cascade classifier because I do not think the detection result should change based on the ROI cropping. If I'm wrong about that, I would love to understand why it does matter. Thanks!static image file, which is loaded via the command line.
#include "opencv2/objdetect.hpp"
#include "opencv2/imgcodecs.hpp"
#include "opencv2/videoio.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/imgproc.hpp"
#include "opencv2/core/utility.hpp"
#include "opencv2/videoio/videoio_c.h"
#include "opencv2/highgui/highgui_c.h"
#include <cctype>
#include <iostream>
#include <iterator>
#include <stdio.h>
using namespace std;
using namespace cv;
// *** /* Function Headers */
void detectAndDisplay( Mat frame );
/* Global variables */
String face_cascade_name = "haarcascade_frontalface_alt.xml";
String eyes_cascade_name = "haarcascade_eye_tree_eyeglasses.xml";
CascadeClassifier face_cascade;
CascadeClassifier eyes_cascade;
String window_name = "Capture - Face detection";
/* @function main */
/*** Mod begin
// parameters used in adjusting the face detection search sub-region
int gFaceSearchRoiX = 0;
int gFaceSearchRoiY = 0;
int gFaceSearchRoiWidthAdj = 0;
int gFaceSearchRoiHeightAdj = 0;
const int kMaxFaceSearchRoiHeightAdjVal = 200;
// *** Mod end
static void help()
{
cout << "\nThis program demonstrates the cascade recognizer. Now you can use Haar or LBP features.\n"
"This classifier can recognize many kinds of rigid objects, once the appropriate classifier is trained.\n"
"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"
" [--try-flip]\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\n"
"During execution:\n\tHit any key to quit.\n"
"\tUsing OpenCV version " << CV_VERSION << "\n" << endl;
}
void detectAndDraw( Mat& img, CascadeClassifier& cascade,
CascadeClassifier& nestedCascade,
double scale, bool tryflip );
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();
const string tryFlipOpt = "--try-flip";
size_t tryFlipOptLen = tryFlipOpt.length();
string inputName;
bool tryflip /*** Mod end */
VideoCapture capture;
Mat frame;
//-- 1. Load the cascades
if( !face_cascade.load( face_cascade_name ) ){ printf("--(!)Error loading face cascade\n"); return -1; };
if( !eyes_cascade.load( eyes_cascade_name ) ){ printf("--(!)Error loading eyes cascade\n"); return -1; };
//-- 2. Read in the image data
inputName.assign( argv[1] );
// get image from provided file
/*** Mod begin */
if(!inputName.empty())
{
frame = false;
help();
CascadeClassifier cascade, nestedCascade;
double scale = 1;
for( int i = 1; i < argc; i++ cv::imread(inputName);
detectAndDisplay( frame );
waitKey(-1);
}
else
/*** Mod end */
{
// get image stream from first camera device
capture.open( -1 );
if ( ! capture.isOpened() ) { printf("--(!)Error opening video capture\n"); return -1; }
while ( capture.read(frame) )
{
cout << "Processing " << i << " " << argv[i] << endl;
if( cascadeOpt.compare( 0, cascadeOptLen, argv[i], cascadeOptLen ) == 0 frame.empty() )
{
cascadeName.assign( argv[i] + cascadeOptLen );
cout << " from which we have cascadeName= " << cascadeName << endl;
printf(" --(!) No captured frame -- Break!");
break;
}
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
//-- 3. Apply the 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( tryFlipOpt.compare( 0, tryFlipOptLen, argv[i], tryFlipOptLen ) == 0 )
{
tryflip = true;
cout << " will try to flip image horizontally to detect assymetric objects\n";
}
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;
help();
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' );
the frame
detectAndDisplay( frame );
int c = inputName.empty() ? 0 : inputName.c_str()[0] - '0' ;
if(!capture) cout << "Capture from CAM " << c << " didn't work" << endl;
}
else waitKey(10);
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( "../data/lena.jpg", 1 );
if(image.empty()) cout << "Couldn't read ../data/lena.jpg" << endl;
}
cvNamedWindow( "result", 1 );
if( capture )
{
cout << "In capture ..." << endl;
for(;;)
{
IplImage* iplImg = cvQueryFrame( capture );
frame = cv::cvarrToMat(iplImg);
if( frame.empty() )
break;
if( iplImg->origin == IPL_ORIGIN_TL )
frame.copyTo( frameCopy );
else
flip( frame, frameCopy, 0 );
detectAndDraw( frameCopy, cascade, nestedCascade, scale, tryflip );
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, tryflip );
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, tryflip );
c = waitKey(0);
if( c (char)c == 27 || c == 'q' || c == 'Q' )
break;
) { break; } // escape
}
else
{
cerr << "Aw snap, couldn't read image " << buf << endl;
}
}
fclose(f);
}
}
}
cvDestroyWindow("result");
return 0;
}
/* @function detectAndDisplay */
void detectAndDraw( Mat& img, CascadeClassifier& cascade,
CascadeClassifier& nestedCascade,
double scale, bool tryflip detectAndDisplay( Mat frame )
{
int {
std::vector<Rect> faces;
Mat frame_gray;
cvtColor( frame, frame_gray, COLOR_BGR2GRAY );
equalizeHist( frame_gray, frame_gray );
//-- Detect faces
face_cascade.detectMultiScale( frame_gray, faces, 1.1, 2, 0|CASCADE_SCALE_IMAGE, Size(30, 30) );
for( size_t i = 0;
double t = 0;
vector<Rect> faces, faces2;
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, COLOR_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0; i < faces.size(); i++ )
{
Point center( faces[i].x + faces[i].width/2, faces[i].y + faces[i].height/2 );
ellipse( frame, center, Size( faces[i].width/2, faces[i].height/2), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
// *** Mod begin
int faceSearchRoiX 360, Scalar( 255, 0, 255 ), 4, 8, 0 );
Mat faceROI = gFaceSearchRoiX;
int faceSearchRoiY = gFaceSearchRoiY;
int faceSearchRoiWidth = smallImg.size().width - gFaceSearchRoiWidthAdj;
int faceSearchRoiHeight = smallImg.size().height - gFaceSearchRoiHeightAdj;
Rect faceSearchRoi = Rect(faceSearchRoiX, faceSearchRoiY,
faceSearchRoiWidth, faceSearchRoiHeight);
Mat subSmallImg = Mat(Size(faceSearchRoi.width, faceSearchRoi.height),
smallImg.type());
subSmallImg = Mat(smallImg, faceSearchRoi);
// *** Mod end
t = (double)cvGetTickCount();
cascade.detectMultiScale( subSmallImg, faces,
frame_gray( faces[i] );
std::vector<Rect> eyes;
//-- In each face, detect eyes
eyes_cascade.detectMultiScale( faceROI, eyes, 1.1, 2, 0
//|CASCADE_FIND_BIGGEST_OBJECT
//|CASCADE_DO_ROUGH_SEARCH
|CASCADE_SCALE_IMAGE
,
0 |CASCADE_SCALE_IMAGE, Size(30, 30) );
if( tryflip for( size_t j = 0; j < eyes.size(); j++ )
{
flip(smallImg, smallImg, 1);
cascade.detectMultiScale( smallImg, faces2,
1.1, 2, 0
//|CASCADE_FIND_BIGGEST_OBJECT
//|CASCADE_DO_ROUGH_SEARCH
|CASCADE_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator r = faces2.begin(); r != faces2.end(); r++ )
{
faces.push_back(Rect(smallImg.cols - r->x - r->width, r->y, r->width, r->height));
}
}
t = (double)cvGetTickCount() - t;
// printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
// *** Mod begin
// output to console
if(faces.size() == 0)
{
cout << "No faces found with search ROI height set to " << img.size().height - gFaceSearchRoiHeightAdj
<< " pixels.\n";
}
// draw ROI
cv::Mat displayImg;
img.copyTo(displayImg);
Rect scaledFaceSearchRoi = faceSearchRoi;
scaledFaceSearchRoi.x *= scale;
scaledFaceSearchRoi.y *= scale;
scaledFaceSearchRoi.width *= scale;
scaledFaceSearchRoi.height *= scale;
rectangle(displayImg, scaledFaceSearchRoi, Scalar(0,0,255), 2);
// *** Mod end
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];
eye_center( faces[i].x + eyes[j].x + eyes[j].width/2, faces[i].y + eyes[j].y + eyes[j].height/2 );
int radius;
double aspect_ratio = (double)r->width/r->height;
if( 0.75 < aspect_ratio && aspect_ratio < 1.3 )
{
center.x = (scale * faceSearchRoiX) + cvRound((r->x + r->width*0.5)*scale);
center.y = (scale * faceSearchRoiY) + cvRound((r->y + r->height*0.5)*scale);
radius = cvRound((r->width cvRound( (eyes[j].width + r->height)*0.25*scale);
eyes[j].height)*0.25 );
circle( displayImg, center, frame, eye_center, radius, color, 3, Scalar( 255, 0, 0 ), 4, 8, 0 );
}
else
rectangle( img, cvPoint(cvRound(r->x*scale), cvRound(r->y*scale)),
cvPoint(cvRound((r->x + r->width-1)*scale), cvRound((r->y + r->height-1)*scale)),
color, 3, 8, 0);
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CASCADE_FIND_BIGGEST_OBJECT
//|CASCADE_DO_ROUGH_SEARCH
//|CASCADE_DO_CANNY_PRUNING
|CASCADE_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 );
}
}
// *** Mod begin
cv::imshow( "result", displayImg );
cv::waitKey(10);
if(gFaceSearchRoiHeightAdj < kMaxFaceSearchRoiHeightAdjVal)
{
gFaceSearchRoiHeightAdj++;
detectAndDraw( img, cascade, nestedCascade, scale, tryflip );
}
// *** Mod end
//-- Show what you got
imshow( window_name, frame );
}
