An approach to image alignment which is based on point-to-point disparities in two images is introduced. A disparity function is defined by considering the image shape structure, and the function parameters are estimated simultaneously from the computation of shape disparity. The decomposition of the disparity function parameters reveals the object rotation, deformation, scaling, and translation in a three-dimensional space. The alignment computation is initially based on measured boundary information and it can also be modified to utilize image gray level change information. Since the computation utilizes all available information and the disparity function is estimated by a least square error criterion, the algorithm is relatively insensitive to noise. The 3-D reconstruction of a sequence of autoradiographic images of a rat brain and several alignment and matching examples are presented. It is shown that the disparity analysis method is general and flexible, and may have application in matching of other medical images such as photon emission tomography and computerized axial tomography.