Stochastic Approximation Approach to Image Registration
Waleed Mohamed, A. Ben Hamza · International Journal of Mathematics & Statistics/International journal of mathematics and statistics · 2010
We present an image alignment method by maximizing a nonextensive entopy-based divergence using a modified simultaneous perturbation stochastic approximation algorithm. Due to its convexity property, this divergence measure attains its maximum value when the conditional intensity probabilities between the reference image and the transformed target image are degenerate distributions. Experimental results on medical images are provided to demonstrate the better registration accuracy of the proposed approach compared to the current state-of-the-art image alignment techniques.