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

In this paper, a hierarchical network modelbased on human vision physiological mechanism was put forward. Firstly, simple celland complex cellin primary visual cortexis 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 extractedby computational modelhave sufficient discrimination; furthermore, the local image features extractedusing biological visual modeldemonstrated much more excellent generalization ability in natural scene with complicated background.