Revision history [back]

Hi all,

e.g. numPos 2000, numNeg 1000, numStages 10, -w 20, -h 20, minHitRate 0.995, maxFalseAlarmRate 0.2

I have some question about collecting neg samples.

1.According to the answer of the article(opencv_traincascade Negative samples training method), is 800 negative samples will be recognize as NEG and 200 negative samples be recognize as POS by 0th stage? If Yes, will those 200 samples be picked up to the next stage?

2.The source code imagestorge.cpp ->NegReader::nextImg

What is meaning of "round"? if the current negative image is 1000x1000 pixels, will be crops many 20x20 images and randomly resizes to predict function? How does the procedure of collect negative samples?

3.Why does the process of "NEG current samples" always be slowly by the high-stages?

Thanks in advance!

Hi all,

e.g. numPos 2000, numNeg 1000, numStages 10, -w 20, -h 20, minHitRate -numPos 2000 -numNeg 1000 -numStages 10 -w 20 -h 20 -minHitRate 0.995, maxFalseAlarmRate -maxFalseAlarmRate 0.2

I have some question questions about collecting neg samples.

1.According 1.According to the answer of the article(opencv_traincascade Negative samples training method), is 800 negative samples will be recognize as NEG and 200 negative samples be recognize as POS by 0th stage? If Yes, will those 200 samples be picked up to the next stage?

2.The 2.The source code imagestorge.cpp ->NegReader::nextImg

What is meaning of "round"? if the current negative image is 1000x1000 pixels, will be crops the image be cropped to many 20x20 images and randomly resizes to resized to predict function? How does the procedure of collect negative samples?