A fuzzy relaxation algorithm for matching imperfectly segmented images to models
Laure J. Chipman, Kiran Ranganath · 2003
A graph theoretic approach for matching imperfectly segmented images with stored scene models is presented. The specific segmentation errors addressed are missing objects, extra objects, missing relations, and mismeasured attributes. By combining enhanced fuzzy relaxation and association graph techniques, the method integrates global inter-object relations and local object attributes to obtain more reliable matching.>