anson0910/CNN_face_detection

3000 images without any faces (negative images)

Opened this issue · 2 comments

dear anson0910:
I am so appreciated your work. I have a question about the 3000 images. Is there a trick to select these negative images? for example: 1. Keep various 2. use the residue part of a image with moving faces out (AFLW dataset) 3. just use some scenery picture?
Look forward your reply.

Hi,
I think it doesn't affect the results a lot, I just chose 3000 scenery pictures from the IMAGENET dataset.

Hi, thanks so much for your help. I have got it.