Register images with deformations (and evaluate quality)

asked 2015-06-11 07:53:06 -0500

lock042 gravatar image

updated 2015-06-11 08:36:47 -0500

Hello everyone, First if any developpers of opencv read this : congratulations for OpenCV3 !! You made a great job. Second, here my questions.

I would like to register a set of planetary images. These images can be deformed between each other due to atmospheric conditions. In order to process the registration I think to do like this:

1 - looking for the better image with high quality

2 - taking this image as reference and find keypoints of other images to this image (the x% of better images)

3 - compute and apply transformation to images in order to take into account the possible deformation with regards to the reference one

Now, my questions are :

For 1 : What is the better way to rate the quality ? I ever heard that contrast could be one of many points to do this, but what else ? In my algorithm I use enthropy but it is not so good. Have you have any idea about some opencv function to help me to do that ?

For 2 : I think that this point is not the most difficult, because OpenCV provides very goods function for that like Feature Detection. If you have another ideas, of course let me know.

For 3 : I think this part is the most difficult and I don't know how to start. Indeed, How to evaluate deformation (because I think once it is evaluated, it will be easy to apply) ?

Finaly, I need to use opencv 2 and not the last version. Thanks.

My best regards

edit retag flag offensive close merge delete