Nonrigid registration based on projected joint entropy combined with gradient similarity
Rafael H. de Souza, Masao Shimizu, Masatoshi Okutomi, Shin Yoshimura · Optical Engineering · 2010
Our study proposes a nonrigid image registration method between different color channels in a color image sequence. It minimizes the entropy in a dominant subspace of the joint distribution of two or more images. The proposed algorithm is based on the observation that the displacement between color channels affects only the dominant subspace in the joint distribution of pixel values. We also propose the use of gradient direction to give extra robustness to our similarity function. Experiments estimating motion parameters for B-spline nonrigid deformation models demonstrate the effectiveness of the proposed registration technique.