Abstract This paper mainly focuses on the issue of generic object scale perception. A computational model in entropy-domain space is presented for scene object description to pursue the underlying entropy manifold in statistical way. The corresponding algorithm approximately follows perceptual hierarchy in human-vision biologically via quad-tree pyramid structure, which can automatically choose the appropriate scale of various objects via proposed scale evaluation function. The sufficient experiments truly demonstrate the effective scale description in entropy region manifold with proper location, and provide additional priori information for object scale perception.
[1] Wang Yizhou,Bahrami S,Zhu Songchun.Perceptual Scale Space and Its Applications.International Journal of Computer Vision,2008,80(1): 143-165 [2] Kang Yousun,Nagahashi H.Depth Perception from a 2D Natural Scene Using Scale Variation of Texture Patterns.IEICE Trans on Information and Systems,2006,E89-D(3): 1294-1298 [3] Henderson J M.Human Gaze Control during Real-World Scene Perception.Trends in Cognitive Sciences,2003,7(11): 498-504 [4] Vogel J,Schiele B.Semantic Modeling of Natural Scenes for Content-Based Image Retrieval.International Journal of Computer Vision,2007,72(2): 133-157 [5] Silva M M,Groeger J A,Bradshaw M F.Attention-Memory Interactions in Scene Perception.Spatial Vision,2006,19(1): 9-19 [6] Oliva A.Gist of the Scene.// Itti L,Rees G,Tsotsos J K,eds.Neurobiology of Attention.SanDiego,USA: Elsevier,2005: 251-256 [7] Dong Le,Izquierdo E.Global-To-Local Oriented Rapid Scene Perception // Proc of the 9th International Workshop on Image Analysis for Multimedia Interactive Services.Klagenfurt,Austria,2008: 155-158 [8] Vogel J,Schwaninger A,Wallraven C,et al. Categorization of Natural Scenes: Local vs.Global Information // Proc of the 3rd Symposium on Applied Perception in Graphics and Visualization.Boston,USA,2006: 33-40 [9] Lazebnik S,Schmid C,Ponce J.Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.New York,USA,2006,Ⅱ: 2169-2178 [10] Bianchi-Berthouze N.Subjective Perception of Natural Scenes: The Role of Color.Proc of the SPIE,2003,5008: 1-13 [11] Assadi A H.Perceptual Geometry of Space and Form: Visual Perception of Natural Scenes and Their Virtual Representation.Proc of the the SPIE,2001,4476: 59-71 [12] Holub A,Perona P.A Discriminative Framework for Modeling Object Classes // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego,USA,2005,Ⅰ: 664-670 [13] Coughlan J,Shen H.Shape Matching with Belief Propagation: Using Dynamic Quantization to Accommodate Occlusion and Clutter // Proc of the Workshop on Computer Vision and Pattern Recognition.Washington,USA,2004: 180-190 [14] Gurevich I B.The Descriptive Techniques for Image Analysis and Recognition // Proc of the 2nd International Conference on Computer Vision Theory and Applications.Barcelona,Spain,2007: 223-229 [15] Adibi P,Safabakhsh R.Joint Entropy Maximization in the Kernel-Based Linear Manifold Topographic Map // Proc of the International Joint Conference on Neural Networks.Orlando,USA,2007: 1133-1138 [16] Shi K,Zhu Songchun.Mapping Natural Image Patches by Explicit and Implicit Manifolds // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Minneapolis,USA,2007: 1-7 [17] Gong Minglun,Yang Y H.Quadtree-Based Genetic Algorithm and Its Applications to Computer Vision.Pattern Recognition,2004,37(8): 1723-1733
2011, Vol. 24 
