Automatic multisensor image registration using wavelet transform

A new method of automatic multisensor image registration based on contour description and contour match is proposed. It first employs the wavelet descriptor moments to represent the contour. Second, a contour matching criteria is presented based on principle of minimum distance classifier; algorithms of contour matching are given according to closed and unclosed contour, respectively. Finally the control points (CPS) are located according to matched contours and consistency checking is employed to remove mismatch control points. The image transformation model and parameter estimation using the rule of least root mean-square error (RMSE) are discussed. The method is accurate, robust, and fast and has been tested on a lot of images. Two experimental results are presented.