A Novel Approach to Corner Matching Using Fuzzy Similarity Measure

Corner matching in sequence images serves as a building block of several important applications of stereo vision. In this paper, we establish the corner correspondence between two images in the presence of intensity variations and motion blur by using a fuzzy theory based similarity measure. The matching approach proposed by us needs to extract set of corner points as candidates from both the frames. Experiments conducted with the help of various sequences of images prove the superiority of our algorithm over standard cross correlation and sum of absolute difference under non-ideal conditions.