Modeling visual perception using similarity representation
Wilbur Peng, Nick DeClaris · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2000
We present a model of 3D visual perception which uses a notion of similarity that preserves meaningful neighborhood relationships between different visual stimuli. The notion involves a similarity graph-based representation that seeks to capture local connectivity in the similarity domain. An end-to-end computational implementation using wavelet features and a multilayer neural network architecture is presented. The usefulness of the similarity representation for visual reasoning is explored.