Revision history [back]

Hi ! I tryed to train HOG and Viola Jones for parts of human bodys, and didn't get very good results. My first try was spleat all objects to big groups like hand, head, leg. But then I understand that HOG can't generalize so differently objects. I broke each group to 2-4 grops witch have objects in same pose and got better results :) I used dlib library, in this lib you can see trained detector like a picture of vectors, maybe it will help you to understand what you have after you trained your classifire.

Hi ! I tryed to train HOG and Viola Jones for parts of human bodys, and didn't get very good results. My first try was spleat all objects to big groups like hand, head, leg. But then I understand that HOG can't generalize so differently objects. I broke each group to 2-4 grops witch have objects in same pose and got better results :) I used dlib library, in this lib you can see trained detector like a picturepicture (g) of vectors, maybe it will help you to understand what you have after you trained your classifire.