Image Registration Module (OpenCV 3.3)

asked 2017-08-18 12:20:24 -0500

hgyoo gravatar image

updated 2017-08-21 13:39:49 -0500

I am familiar with image registration in MATLAB. I now want to completely switch over to OpenCV in C++ and need some guidance.

OpenCV 3.3 has a module named Image Registration (http://docs.opencv.org/trunk/db/d61/g...). I found users with older release have used several techniques (e.g., ORB, SIFT, SURF) to calculate degree of transformation and then applied the transformation to obtain registered images. How are these techniques different from the ones in the image registration module cv::reg ?

Adding a clarification to my original question, I wanted to know how these techniques are different from each other (e.g., pixel-based vs. feature-based) before figuring out which one to use for my application.

Since my original posting, I learned the Image Registration module is part of the extra "contrib" module package and is similar/identical to the one published by Alfonso Sanchez-Beato at least 3 years ago (https://github.com/opencv/opencv_cont...). The technique is pixel based.

I would appreciate if anyone could chip in or point to a summary of various registration techniques.

edit retag flag offensive close merge delete

Comments

what do you want to do ?

LBerger gravatar imageLBerger ( 2017-08-20 02:52:22 -0500 )edit

Hi LBerger. At this time I am interested in learning what techniques are readily available in the release 3.3+. I updated my original question with a clarification. Than you.

hgyoo gravatar imagehgyoo ( 2017-08-21 13:42:20 -0500 )edit

Sorry not enough time to help you but I think all methods are used in test code

LBerger gravatar imageLBerger ( 2017-08-22 03:22:20 -0500 )edit