Synthesis and Optimization of a Stochastic Algorithm for Image Registration Using Shannon’s Maximum Mutual Information Criterion
摘要
Abstract
An algorithm for estimating image registration parameters using Shannon’s maximum mutual information criterion is synthesized on the basis of the mathematical methods of stochastic gradient adaptation. Expressions for the gradient of mutual information are obtained. At the same time, the derivatives of the entropy of images with respect to the estimated parameters are found using the Parzen window method. The synthesized algorithm is optimized to improve performance.