Abstract
An image matching algorithm is presented in order to get an accurate matching for dense image points. The main idea is using multiple constrains including affine transformation, epipolar geometry, gray-scale correlation and RGB correlation to do step by step approximation for the matching points. Affine transformation constrain is used for getting the regional similarity of the image points, and then epipolar constraint, gray scale relativity constrain are applied in the matching algorithm to get further approximation, a new RGB correlation matching algorithm is specially used in the final step aimed to get the exact match of feature points. The matching error is checked by epipolar geometry constraint and unique constrain to prune out the incorrect matched points. Experimental results show that this algorithm converges fast and increase matching accuracy effectively.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
