I’m trying to implement the Viola Johns face detection algorithm on Cuda platform (I’m aware that openCV already did that, I do that for my school).
My first phase is to implement the algorithm on CPU.
I’m using openCV library, I know openCV knows how to do face detection, In order to understand, I would like to get back to basic and do it my own way.
I created the integral sum representation, and the squere sum integral representation using openCV function.
I iterated through the cascade. iterated through the stages, classfiers and rects. Normalized each window, calculated the sum of each classifer and compared to the threshold, Sadly it’s seems like I’m missing something. because I can’t detect faces.
It seems like I need to get better understanding of the the cascade XML file.
Here is an example:
<!-- tree 158 -->
<_>
<!-- root node -->
<feature>
<rects>
<_>3 6 2 2 -1.</_>
<_>3 6 1 1 2.</_>
<_>4 7 1 1 2.</_></rects>
<tilted>0</tilted></feature>
<threshold>2.3729570675641298e-003</threshold>
<left_val>0.4750812947750092</left_val>
<right_val>0.7060170769691467</right_val></_></_>
<_>
<!-- tree 159 -->
<!-- tree 159 -->
<_>
<!-- root node -->
<feature>
<rects>
<_>16 6 3 2 -1.</_>
<_>16 7 3 1 2.</_></rects>
<tilted>0</tilted></feature>
<threshold>-1.4541699783876538e-003</threshold>
<left_val>0.3811730146408081</left_val>
<right_val>0.5330739021301270</right_val></_></_></trees>
<stage_threshold>79.2490768432617190</stage_threshold>
<parent>16</parent>
<next>-1</next></_>
<_>
I’d like to understand what is the meaning of the left_val and the right_val? What is the meaning of the parent, next values? How to calculate each classifier normalized sum? Is there anything I’m doing wrong here?
See my code attached.
int RunHaarClassifierCascadeSum(CascadeClassifier * face_cascade, CvMat* image , CvMat* sum , CvMat* sqsum,
CvMat* tilted,CvSize *scaningWindowSize, int iteratorRow, int iteratorCol )
{
// Normalize the current scanning window - Detection window
// Variance(x) = E(x^2) - (E(x))^2 = detectionWindowSquereExpectancy - detectionWindowExpectancy^2
// Expectancy(x) = E(x) = sum_of_pixels / size_of_window
double detectionWindowTotalSize = scaningWindowSize->height * scaningWindowSize->width;
// calculate the detection Window Expectancy , e.g the E(x)
double sumDetectionWindowPoint1,sumDetectionWindowPoint2,sumDetectionWindowPoint3,sumDetectionWindowPoint4; // ______________________
sumDetectionWindowPoint1 = cvGetReal2D(sum,iteratorRow,iteratorCol); // |R1 R2|
sumDetectionWindowPoint2 = cvGetReal2D(sum,iteratorRow+scaningWindowSize->width,iteratorCol); // | | Sum = R4-R2-R3+R1
sumDetectionWindowPoint3 = cvGetReal2D(sum,iteratorRow,iteratorCol+scaningWindowSize->height); // |R3________________R4|
sumDetectionWindowPoint4 = cvGetReal2D(sum,iteratorRow+scaningWindowSize->width,iteratorCol+scaningWindowSize->height);
double detectionWindowSum = calculateSum(sumDetectionWindowPoint1,sumDetectionWindowPoint2,sumDetectionWindowPoint3,sumDetectionWindowPoint4);
const double detectionWindowExpectancy = detectionWindowSum / detectionWindowTotalSize; // E(x)
// calculate the Square detection Window Expectancy , e.g the E(x^2)
double squareSumDetectionWindowPoint1,squareSumDetectionWindowPoint2,squareSumDetectionWindowPoint3,squareSumDetectionWindowPoint4; // ______________________
squareSumDetectionWindowPoint1 = cvGetReal2D(sqsum,iteratorRow,iteratorCol); // |R1 R2|
squareSumDetectionWindowPoint2 = cvGetReal2D(sqsum,iteratorRow+scaningWindowSize->width,iteratorCol); // | | Sum = R4-R2-R3+R1
squareSumDetectionWindowPoint3 = cvGetReal2D(sqsum,iteratorRow,iteratorCol+scaningWindowSize->height); // |R3________________R4|
squareSumDetectionWindowPoint4 = cvGetReal2D(sqsum,iteratorRow+scaningWindowSize->width,iteratorCol+scaningWindowSize->height);
double detectionWindowSquareSum = calculateSum(squareSumDetectionWindowPoint1,squareSumDetectionWindowPoint2,squareSumDetectionWindowPoint3,squareSumDetectionWindowPoint4);
const double detectionWindowSquareExpectancy = detectionWindowSquareSum / detectionWindowTotalSize; // E(x^2)
const double detectionWindowVariance = detectionWindowSquareExpectancy - std::pow(detectionWindowExpectancy,2); // Variance(x) = E(x^2) - (E(x))^2
const double detectionWindowStandardDeviation = std::sqrt(detectionWindowVariance);
if (detectionWindowVariance<=0)
return -1 ; // Error
// Normalize the cascade window to the normal scale window
double normalizeScaleWidth = double(scaningWindowSize->width / face_cascade->oldCascade->orig_window_size.width);
double normalizeScaleHeight = double(scaningWindowSize->height / face_cascade->oldCascade->orig_window_size.height);
// Calculate the cascade for each one of the windows
for( int stageIterator=0; stageIterator< face_cascade->oldCascade->count; stageIterator++ ) // Stage iterator
{
CvHaarStageClassifier* pCvHaarStageClassifier = face_cascade->oldCascade->stage_classifier + stageIterator;
for (int CvHaarStageClassifierIterator=0;CvHaarStageClassifierIterator<pCvHaarStageClassifier->count;CvHaarStageClassifierIterator++) // Classifier iterator
{
CvHaarClassifier* classifier = pCvHaarStageClassifier->classifier + CvHaarStageClassifierIterator;
float classifierSum=0.;
for( int CvHaarClassifierIterator = 0; CvHaarClassifierIterator < classifier->count;CvHaarClassifierIterator++ ) // Feature iterator
{
CvHaarFeature * pCvHaarFeature = classifier->haar_feature;
// Remark
if (pCvHaarFeature->tilted==1)
break;
// Remark
for( int CvHaarFeatureIterator = 0; CvHaarFeatureIterator< CV_HAAR_FEATURE_MAX; CvHaarFeatureIterator++ ) // 3 Features iterator
{
CvRect * currentRect = &(pCvHaarFeature->rect[CvHaarFeatureIterator].r);
// Normalize the rect to the scaling window scale
CvRect normalizeRec;
normalizeRec.x = (int)(currentRect->x*normalizeScaleWidth);
normalizeRec.y = (int)(currentRect->y*normalizeScaleHeight);
normalizeRec.width = (int)(currentRect->width*normalizeScaleWidth);
normalizeRec.height = (int)(currentRect->height*normalizeScaleHeight);
double sumRectPoint1,sumRectPoint2,sumRectPoint3,sumRectPoint4; // ______________________
sumRectPoint1 = cvGetReal2D(sum,normalizeRec.x,normalizeRec.y); // |R1 R2|
sumRectPoint2 = cvGetReal2D(sum,normalizeRec.x+normalizeRec.width,normalizeRec.y); // | | Sum = R4-R2-R3+R1
sumRectPoint3 = cvGetReal2D(sum,normalizeRec.x,normalizeRec.y+normalizeRec.height); // |R3________________R4|
sumRectPoint4 = cvGetReal2D(sum,normalizeRec.x+normalizeRec.width,normalizeRec.y+normalizeRec.height);
double nonNormalizeRect = calculateSum(sumRectPoint1,sumRectPoint2,sumRectPoint3,sumRectPoint4); //
double sumMean = detectionWindowExpectancy*(normalizeRec.width*normalizeRec.height); // sigma(Pi) = normalizeRect = (sigma(Pi- rect) - sigma(mean)) / detectionWindowStandardDeviation
double normalizeRect = (nonNormalizeRect - sumMean)/detectionWindowStandardDeviation; //
classifierSum += (normalizeRect*(pCvHaarFeature->rect[CvHaarFeatureIterator].weight));
}
}
// if (classifierSum > (*(classifier->threshold)) )
// return 0; // That's not a face !
if (classifierSum > ((*(classifier->threshold))*detectionWindowStandardDeviation) )
return -stageIterator; // That's not a face ! , failed on stage number
}
}
return 1; // That's a face
}
You need to make some big changes. First of all classifier->threshold is a threshold for each feature. classifier->alpha points to an array made of 2 elements – left_val and right_val(to my understanding). You should put something like this after the classifier loop-
then compare stage_sum with CvHaarStageClassifier::threshold which is the stage threshold, loop through stage_classifiers[i] .if it passes all of them then its a face!
‘parent’ and ‘next’ are useless here if you use haarcascade_frontalface_alt.xml, it is just a stump based cascade and not a tree based.