How is acceptance ratio calculated? [closed]
I've been working with Object Training for a while now, and I've found that generally cascades with an acceptance ratio of .0002 to .0007 are the most refined generally. However, I don't quite understand how acceptance ratio is calculated using traincascade. Could someone explain it to me or point me to a good reference that explains it?
Possible duplicate of http://answers.opencv.org/question/37675/how-is-acceptance-ratio-caclulated/