FAST or AGAST on Color Images

asked 2015-11-19 04:30:01 -0500

Adi gravatar image

updated 2015-11-19 08:55:51 -0500

I want to detect tiny dark points/dots in a color image.
Is there an easy way to get FAST and/or AGAST to measure the score as the difference between the min-of-channels in the center p and the max-of-channels in the points around each center?

If this is not possible with the current API, how would one change FAST or AGAST to accept 2 images, one for the center and one for the outline?

Here's an example. It has two darker faint spots:
image description

The background is also noisy (and even more in other cases).
FAST and AGAST can actually detect the spot closer to the center, but the one on the bottom-right corner cannot be detected without detecting a lot of noise.

Since FAST/AGAST work only on gray-scale images, it would be a great addition if we could use 2 inputs, one for the center-pixel and one for the surrounding pixels.

edit retag flag offensive close merge delete


Hmmm I am not sure if using keypoint detectors/descriptors is actually the way you want to move forward. Could you supply us with a test image of your case?

StevenPuttemans gravatar imageStevenPuttemans ( 2015-11-19 07:32:38 -0500 )edit

I added a sample. Both FAST and AGAST are very fast corner detectors, or center-surround contrast estimators. They're just the right approach for what I need, and in fact give pretty good results already. I am looking for generalize them just a bit more.

Adi gravatar imageAdi ( 2015-11-19 08:58:04 -0500 )edit