Tal Darom's profile - activity

2013-09-10 11:32:11 -0600	asked a question	traincascade lbp implementation I'm trying to understand the implementation of traincascade with lbp features. More specifically I'm looking for the implementation of the lbp weak classifier. From looking at the macro CV_DTREE_CAT_DIR it seems that for each sample each feature is multiplied 256 times with value of 1 if the binary feature value is equal to the same feature of the image, and 0 otherwise. but I can't find where in code this is calculated.
2013-07-11 09:14:46 -0600	commented question	Parallelization of linear part of opencv_traincascade Hi, if you want to share the code I might be able to port it to TBB (or better - to cv::parallel_for_)
2013-07-10 06:26:39 -0600	asked a question	Parallelization of linear part of opencv_traincascade opencv_traincascade is parallelized using TBB but not completly. There is a pretty large linear part, notebly in `updateTrainingSet()`. When training the 20th stage and looking for 10,000 negative samples (for example) you have to search through 19^2*10,000 samples which takes a lot of time. Does any one know if there is any intension to parallelize this part? (If not - I might do that myself).