The focus is on getting a very precise alignments between pairs of different views of the same object to avoid distortion of the 3D model, in contrast to most previous work, the couple see may indicate relatively little overlap and do not need prealigned. This measure quantifies the interleaving of the two surfaces as they smooth alignment, placing the qualitative evaluation "splotchiness," is often used in reference to the rendering of surfaces parallel, into a solid mathematical foundation. The authors go to combine the SIM with Genetic Algorithms (GAs) to develop a robust approach for registration of range images. The results confirm that this technique achieve proper registration of the surface with no need prealignment, compared with methods based on the Iterative Closest Point (ICP) algorithm, the most popular for the moment.