Ask Your Question

Feature detection of edges

asked 2013-03-11 02:20:01 -0600

Nick Wareing gravatar image

Are there any feature detectors that do a good job of matching images that have previously had an edge detection algorithm run over them?

The context of this question is that I have two images which are x-rays of a person's mouth, but taken at different times, such that: a). the new angle of the x-ray is slightly different. b). the teeth may have moved/changed slightly.

I am planning to use feature detection to then get a homography which will allow me to twist the second image to align with the first, so that I can then compare them.

Here is one of the images after using Canny edge detection:


Thanks in advance for any suggestions of feature detectors, or any suggestions on how else I might approach this problem.

edit retag flag offensive close merge delete

2 answers

Sort by ยป oldest newest most voted

answered 2013-06-06 01:18:16 -0600

SR gravatar image

Align the images by using local feature correspondences on the original image. I doubt that an automatic alignment of the canny edge images is possible.

Avoid canny where possible as it does not yield stable edges. If you need an edge image then just display/use the plain Sobel filter output.

edit flag offensive delete link more

answered 2013-03-11 10:54:21 -0600

What I would suggest is to apply one of the feature detectors on the image that can be found inside the feature2d library:

Basicly use the feature points extracted by SURF, SIFT, ORB, FREAK, BRISK, ... to match both image by searching for matching feature points. The discriptor matching functionality of openCV will help out there. These descriptors create a unique representation of the area around the feature points and try to retrieve them.

By using these feature points, and looking at local features, you do not have to align both images.

edit flag offensive delete link more

Question Tools


Asked: 2013-03-11 02:20:01 -0600

Seen: 1,000 times

Last updated: Jun 06 '13