This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
a)numPos < number of samples in vec
b)choosing minhitrate and maxfalsealarm
For example you have 1000 positive samples. You want your system to detect 900 of them for training. So desired hitrate = 900/1000 = 0.9. Commonly, put minhitrate = 0.999^number of stages
For example you have 1000 negative samples. Because it’s negative, you don’t want your system to detect them. But your system, because it has error, will detect some of them. Let error be about 490 samples, so false alarm = 490/1000 = 0.49. Commonly,put false alarm = 0.5^number of stages
c)vec-file has to contain >= (npos + (numStages-1) * (1 – minHitRate) * numPose) + S, where S is a count of samples from vec-file.S is a count of samples from vec-file that can be recognized as background right away.
d)The more the number of negative images,more the traincascade uses the samples to train every step.I wont day you should reduce the number of negative images but keep it optimal.
e)I am not perfectly sure but Pos Count consumed gives the number of positive images you mentioned to use for train : number of random images it took from vec file to choose the required number you mentioned.The neg count consumed specifies the ratio of negative images that got used in the process of false training in that particular stage.Please verify this once.
Hope this helps you :)
