Training haar classifier.

asked 2013-09-20 04:57:50 -0500

MattiasR gravatar image

A question about creating my own .xml file.

I've read that as many photos (positive and negative) should be used do increase the accuracy of the trained haar classifier.

But. Lets say, that I have a collection of 1000 pos.3000 neg. photos, and create my file. And compare that with a collection of about 1 000 000 pos, 3 000 000 negative. (yes, it will take some time :) ) Isnt the last xml file going to be so huge that it is impossible to use it for face tracking?

Or. I can ask the question in anoter way: The size of the final classifier file, does it depend on the amount of photos used during traing?

Thanks for reading!

edit retag flag offensive close merge delete

Comments

1

"The size of the final classifier file, does it depend on the amount of photos used during traing?"

no, the size is more dependant on the number of stages used.

but it will take forever with 4 mill images. and apart from the numbers, the quality of your positives might matter more than their count, i.e. if your real life situation has your 'thing' against a cluttered background, and you traind it with images against a plain bg.

berak gravatar imageberak ( 2013-09-20 05:24:22 -0500 )edit

Thank you! yeah, i used 4 mill, just to have a number that where much much greater than the first alternative.

MattiasR gravatar imageMattiasR ( 2013-09-20 05:33:02 -0500 )edit