Artificial Visual Cortical Responding Model in Image Semantic Processing

This paper used the time sequence response feature, which generated from a novel visual information process model named Artificial Visual Cortical Responding Model (AVCRM), to clustered the sub-images into the initially manually assigned concept categories to attain the semantic distribution map of the image. According to the result of semantic distribution map, the semantic descriptor was generated for further semantic based Content Based Image Retrieval system. This mechanism was proved to be effective through the experiments and made a good semantic foundation of the future content based image retrieval research work.