prala123's profile - activity

I found the problem, my input image height had the same height as the trained window, now it is height +1 and it is working : )

i found the problem, my input image height had the same height as the trained window, now it is height +1 and it is working : )

Hi guys, sorry to bother again.

But when I run the the detectMultiScale on a trained cascade classifier nothing is ever detect, no rectangles. Weird thing is even with just one stage i get good results using LBP here is my results.

POS count : consumed   2000 : 2000
NEG count : acceptanceRatio    4000 : 1
Precalculation time: 0.196
+----+---------+---------+
|  N |    HR   |    FA   |
+----+---------+---------+
|   1|    0.965|  0.08575|
+----+---------+---------+

and this is how i call the classifier ...

classifier.detectMultiScale(testMat, rectangles, 1.1, 0, 0, cv::Size(30, 30), cv::Size(50,50));

Any hint on why this is happening?

Thanks

Yeah trouble was exactly that my pos neg ratio was not the recommended. And some samples did not have the path correct, you are right. Now it is working, and it is on stage 7 ... yay. Thanks for the reply.

While trying to train a cascade classifier opencv_traincascade process always halts at stage 4.

I have 7358 of negative samples. where i list their relative path in the negative_samples file, and I have 17600 positive samples in the positives.vec file.

opencv_traincascade -data cascade -vec samples/positives.vec -bg negative_samples -numStages 20 -precalcValBufSize 10 -precalcIdxBufSize 200 -acceptanceRatioBreakValue 0.0001 -w 50 -h 50 -mode ALL -maxWeakCount 100 -maxDepth 1 -weightTrimRate 0.95

here is the console output