Adaptive image matching via spatial varying gray-level correction

This paper deals with the adaptive image matching and displacement estimation problems of dissimilar sequential images. Adaptive matching may be referred to a kind of functional optimization. Based on the additive measuring model for sequential images with gray-level deviation and the finite element technique, a class of gray-level correction model and robust matching criterion function are proposed, and an adaptive hierarchical searching algorithm is studied, which can automatically evaluate the temporal and spatial gray-level deviation existed in sequential images and filter out the interference thereof to increase the probability of correct estimation of displacement. Experimental results for the estimation of displacement fields with translation and/or small angle rotation in medical digital subtraction angiography (DSA) imaging and aerial remote sensing pictures are presented