A bio-inspired image local feature representation based on vision network model

Abstract

In this paper, a hierarchical network model based on human vision physiological mechanism was put forward. Firstly, simple cell and complex cell in primary visual cortex is modeled, then studied the response pattern of V4 area and inferior temporal cortex on ventral side channel and representing the local features of input image utilized the computational model. The experiment results show that local image features extracted by computational model have sufficient discrimination; furthermore, the local image features extracted using biological visual model demonstrated much more excellent generalization ability in natural scene with complicated background.