Doubts about training data
Closed this issue · 1 comments
xstz commented
I have two question;
- In the example, the data: - img_files/.bmp, - mnt_files/.mnt , - seg_files/*.jpg. is needed when train the corasenet, the orientation field of the fingerprint is not necessary. but the net include a function about enhancement the raw fingerprint image(gaber filter). I don't understand how the gaber filter get the orientation? and there is no loss function for the orientation.
- The mnt_files/.mnt file include the orientation about the minutiae. i want to know the format about the 0~ 2pi ? or others.
luannd commented
Sorry for late reply.
- That function enhances the image to get a robust orientation field. We use that orientation as minutiae orientation in this code.
- Yes. 0~2pi (if I remember correctly)