A Hierarchial Model for Visual Perception

Abstract

This paper proposes a computational model for visual perception: the visual pathway is considered as a functional process of dimensionality reduction for input data, that is, to search for the intrinsic dimensionality of natural scene images. This model is hierarchically constructed, and final leads to the formation of a low-dimensional space called perceptual manifold. Further analysis of the perceptual manifold reveals that scene images which share similar perceptual similarities stay nearby in the manifold space, and the dimensions of the space could describe the spatial layout of scenes, which are like the degree of naturalness, openness supervised trained in (Oliva, A., and Torralba, A. Int. J. Comput. Vis. 42 (2001) 145175). Moreover, the implementation of scene retrieval task validates the topographic property of the perceptual manifold space.