This technique allows for global information to be incorporated in the evaluation of triplets of mappings.
About
Description: This technique provides an approach to registering multimodal and/or monomodal images by building key point correspondences. For each test key point, a number of reference key points are chosen as mapping candidates. A triplet of key point mappings determine an affine transformation that is evaluated using a similarity metric between the reference image and the transformed test image by the determined transformation. An iterative process is conducted on triplets of key point mappings, keeping track of the best matched reference key point. The similarity metric is defined to be the number of overlapped edge pixels over the entire images, allowing for global information to be incorporated in the evaluation of triplets of mappings.