deep-landmark icon indicating copy to clipboard operation
deep-landmark copied to clipboard

how to solve the face just on the edge of the image?

Open wuqiangch opened this issue 9 years ago • 2 comments
trafficstars

@luoyetx When a human face in an image is just on the edge of the image. There is always such a problem: out of bounds.Because in the process of recognition, there are several images of cutting. Out of the image boundary Will appear.

wuqiangch avatar Mar 15 '16 09:03 wuqiangch

I wonder if your detector can find out this kind of faces. I'm not sure whether the network can predict landmarks or not, since the training data may be lack of such faces, I think the result won't be good, but you can try.

luoyetx avatar Mar 15 '16 11:03 luoyetx

@wuqiangch I would recommend to pad the image by zeros (I use pad_size=10 pixels) to avoid boundary problems. pad_img=numpy.pad(img, ((10,10),(10,10)),'constant') After the point detection procedure, be aware to take off pad_size on both x and y axis to recover the original coordinate system.

ikvision avatar Mar 30 '16 18:03 ikvision