Ask Your Question

Region of interest for Haar samples?

asked 2016-09-23 22:08:06 -0500

roboteyes gravatar image

updated 2016-09-23 22:36:47 -0500

I've noticed with many face detection algorithms, that the detected region of interest closely crops the eyes and mouth... excluding ears, hair and chin. When collecting and cropping my positive sample collection, should I tightly crop ensuring that no background is visible, or loosely crop the region?

See my example:

image description

My guess is the right hand side, but I'd just like to double-check with the experts here.

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted

answered 2016-09-24 06:20:58 -0500

Eduardo gravatar image

updated 2016-09-24 06:27:41 -0500

For Viola & Jones algorithm, you can take a look at the corresponding paper and at the dataset they used.

You can also check at some face detection datasets (be careful at the dates):

Just my opinion as a non expert: you should crop between your two examples as the left example contains too much background in my opinion and the right one seems to me too cropped. As the training process will select relevant features (at least with old algorithms like Viola & Jones, I don't know how it is with DNN algorithms), some litlle background should be harmless I think. The faces have to be consistent, always at the same size and at the same position in the dataset.

edit flag offensive delete link more



Helpful paper, thanks! A few extracts

"The training faces are only roughly aligned."

"place a bounding box around each face just above the eyebrows and about half-way between the mouth and the chin"

So think you're right. A little-less cropped, but only slightly.

roboteyes gravatar imageroboteyes ( 2016-09-24 12:10:26 -0500 )edit
Login/Signup to Answer

Question Tools

1 follower


Asked: 2016-09-23 22:08:06 -0500

Seen: 101 times

Last updated: Sep 24 '16