A Maximum Likelihood Approach for Image Registration Using Control Point And Intensity

Registration of multidate or multisensor images is an essential process in many image processing applications including remote sensing, medical image analysis, and computer vision. Control point (CP) and intensity are the two basic features used separately for image registration in the literature. In this paper, an exact maximum likelihood (EML) registration method, which combines both CP and intensity, is proposed for image alignment. The EML registration method maximizes the likelihood function based on CP and intensity to estimate the registration parameters, including affine transformation and CP coordinates. The explicit formulas of the Cramer–Rao bound (CRB) are also derived for the proposed EML and conventional image registration algorithms. The performances of these image registration techniques are evaluated with the CRBs.