Display Haar features from a trained AdaBoost classfier

asked 2013-02-22 22:53:13 -0600

ythen
96 ●1 ●1 ●7

Is there a way to display visually which Haar features are used at every stage of the classifier?

I have recently trained a classfier to detect vehicles, using opencv_traincascade.exe. For further analysis, I would like to see the features being evaluated at every stage.

Thanks for your help.

It will be great if anyone can supply information about the cascade.xml, what are the meaning of the nodes. Thanks

This question has also been asked here.

edit retag flag offensive close merge delete

add a comment

1 answer

Sort by » oldest newest most voted

answered 2013-02-24 01:36:39 -0600

Bibliarij

136 ●1 ●4

Here http://makematics.com/research/viola-jones/ guy realized your idea.

edit flag offensive delete link

Comments

great find! i actually contacted adam yesterday and he provided me with some codes. Anyways, now that I know, I still need to know which features are being tested at a particular stage and node. I would be great if anyone able to help

ythen ( 2013-02-24 09:23:05 -0600 )edit

Hi, i have a similar project with yours, but car detection in this case, i was wondering to have the source code for haar-feature extraction process visualization just like adam did, http://vimeo.com/12774628

can i have the code too? thanks.