2015-11-08 02:52:07 -0600 | commented answer | Missing HOG Cascade in Ver 3 my bad. i am using cv2 in detection but cv3 in training (as above). |
2015-11-06 00:47:36 -0600 | commented question | lbp cascade didnt produce classifier.xml |
2015-11-06 00:28:40 -0600 | commented answer | Missing HOG Cascade in Ver 3 hmm i see.. but it seems that i am calling it in detection and getting decent results. i guess its because its still in the python api? as im using python. nowhere do i tell it to use a particular evaluator, i just tell it about the classifier and then call detectMultiscale .. |
2015-11-03 21:14:25 -0600 | commented answer | Missing HOG Cascade in Ver 3 but i call |
2015-11-01 21:38:32 -0600 | received badge | ● Editor (source) |
2015-11-01 21:36:29 -0600 | asked a question | lbp cascade didnt produce classifier.xml ive trained a few haar and hog 20 stage classifiers using train_cascade. And when they seemed to not train anymore, id cancel and still load the provided stages and have a classifier.xml up to that stage that i could use. But my latest lbp that i trained doesnt have a classifier.xml only the (stage1.xml ... stage15.xml) and params.xml Any reason this lbp one hasnt? Can i manually combine the stage xmls to do the same? This batch of trainings has been using 1000:4000 (pos:neg) samples |
2015-11-01 21:26:30 -0600 | commented answer | Missing HOG Cascade in Ver 3 so.. it is not documented anymore but is still callable? because im pretty sure im calling it and getting back a classifier that seems to work decently in certain params and situations (opencv 3 python API) |
2015-06-01 00:58:33 -0600 | received badge | ● Enthusiast |
2015-05-30 02:09:10 -0600 | commented question | Does OpenCV 3.0 actually have car detection? real-time car detection can be achieved using Viola Jones framework with traincascade, which uses Adaboost, Waldboost is an optimal algorithm for Adaboost. |
2015-05-06 12:29:57 -0600 | received badge | ● Supporter (source) |