Abstract Inspired by the research of visual systems in neuroanatomy and psychology, a novel model for salient region detection based on “what” and “where” pathways in an image is proposed in this paper. The operation of the model can be divided into two stages: finding and shifting salient regions. Current salient region and potential targets of an image are firstly found and marked according to statistical feature saliency. Series of next salient regions are then detected by altering different current salient region and alterative attracting force computation. Experimental results with natural images demonstrate its effectiveness and robustness.
[1] Rybak I A, Gusakova V I, Golovan A V, et al. A Model of Attention-Guided Visual Perception and Recognition. Vision Research, 1998, 38(15-16): 2387-2400 [2] Itti L, Koch C. Computational Modeling of Visual Attention. Nature Reviews Neuroscience, 2001, 2(3): 194-203 [3] Zhang P, Wang R S. Detecting Salient Regions Based on Location Shift and Extent Trace. Journal of Software, 2004, 15(6): 891-898 (in Chinese) (张 鹏,王润生.基于视点转移和视区追踪的图像显著区域检测.软件学报, 2004, 15(6): 891-898) [4] Kronauer R E, Zeevi Y Y. Reorganization and Diversification of Signals in Vision. IEEE Trans on System, Man, Cybernetics, 1985, 15(1): 91-101 [5] Long P H, Zheng N N. Multiresolution Edge Detection Based on Nonuniform Sampling and Selective Attention Mechanism. Acta Electronica Sinica, 1998, 26(5): 97-99 (in Chinese) (龙甫荟,郑南宁.基于非均匀采样及选择注意机制的多分辨率边缘检测.电子学报, 1998, 26(5): 97-99) [6] Creem S H, Proffitt D R. Defining the Cortical Visual Systems: “What”, “Where”, and ”How”. Acta Psychologica, 2001, 107(1-3): 43-68 [7] Hyvrinen A, Oja E. Independent Component Analysis: Algorithms and Applications. Neural Networks, 2000, 13 (4-5): 411-430 [8] Klein R M. Inhibition of Return. Trends in Cognitive Sciences, 2000, 4(4): 138-148 [9] Zabrodsky H, Peleg S. Attentive Transmission. Journal of Visual Communication and Image Representation, 1990, 1(2): 189-198 [10] Hyvrinen A. Fast and Robust Fixed-Point Algorithms for Independent Component Analysis. IEEE Trans on Neural Networks, 1999, 10 (3): 626-634 [11] Image Sequence Server. 1997. http://i21www.ira.uka.de/image_sequences
2006, Vol. 19 
