A Hierarchial Model for Visual Perception

摘要：

This paper proposes a computational model for visual perception: the visual pathway is considered as a functional process of dimensionality reduction forinput 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) 145-175). Moreover, the implementation of scene retrieval task validates the topographic property of the perceptual manifold space.

关键词： Sparse coding Hierarchical model Computational vision

作者: Bolei Zhou Liqing Zhang

作者单位: MOE-Microsoft Laboratory for Intelligent Computing and Intelligent Systems, Department of Biomedical Engineering Shanghai Jiao Tong University, Shanghai, China

会议类型: 国际会议

会议名称: The Second International Conference on Cognitive Neurodynamics--2009(第二届国际认知神经动力学会议)

会议地点: 杭州

会议语种:英文

页码: 607-614

在线出版日期: 2009-11-15（万方平台首次上网日期，不代表论文的发表时间）