Mental Image Transformation and Matching using Surface Reconstruction Neural Networks

Invariant 2-D/3-D object recognition and motion estimation under detection/occlusion noise and/or partial object viewing are di cult pattern recognition tasks. On the other hand, the biological neural networks of human are extremely adept in these tasks. It has been suggested by the studies of experimental psychology that the task of matching rotated and scaled shapes by human is done by mentally rotating and scaling gradually one of the shapes into the orientation and size of the other and then testing for a match. Motivated by these studies, we present a novel and robust neural network solution for these tasks based on detected surface boundary data or range data. The method operates in two stages: The object is rst parametrically represented by a surface reconstruction neural network (SRNN) trained by the boundary points sampled from the exemplar object. When later presented with boundary points sampled from the distorted object without point correspondence, this parametric representation allows the mismatch information back-propagate through the SRNN to gradually determine (align) the best similarity transform of the distorted object. The distance measure can then be computed in the reconstructed representation domain between the surface reconstructed exemplar object and the aligned distorted object. Applications to invariant 2-D target classi cation and 3-D object motion estimation using sparse range data collected from a single aspect view are presented.