A biologically inspired shape representation model based on part decomposition

Shape representation is a major challenge in machine perception, and is the basis for vision. Most current theories of shape representation are based on the idea of feature or part extraction. Compared with template matching and Fourier decomposition, parts-based mechanism is better adapted to the real-world difficulties of view-point transformations, partial occlusion and plastic deformation. We present in this paper a parts-based shape representation model inspired by the mammalian visual ventral pathway. With the sparse coding constraint, the computational model combines unsupervised representation in the feed-forward stream with lateral interaction to achieve stable, efficient and natural representation of shapes. Further comparing the response properties of model cells to those of biological V4 cells, we find that model cells display same curvature and object centered tuning as the reported physiological measurements.