Abstract How to simulate the human visual perception system in order to build a robust and unsupervised computational model for salient edges detection on object contours in natural images is the main content in this paper. Firstly, the salient object sub-region is determined. Secondly, the low-level visual features of texture and color are analyzed to obtain a group of potential salient contour edges. Next, a graph model is established by analyzing the closure between any two potential salient edges. Finally, Dijkstras algorithm is used to obtain the salient contour edges. The experimental results of natural images show the proposed model is feasible and its biological rationality is verified.
[1] Martin D R, Fowlkes C C, Malik J. Learning to Detect Natural Image Boundaries Using Local Brightness, Color and Texture Cues. IEEE Trans on Pattern Analysis and Machine Intelligence, 2004, 26(5): 530-549 [2] Martin D R, Fowlkes C C, Malik J. Learning to Detect Natural Image Boundaries Using Brightness and Texture[EB/OL]. [2009-07-01]. books.nips.cc/papers/files/nips15/VS02.pdf [3] King D B, Wertheimer M. Max Wertheimer and Gestalt Theory. New Brunswick, USA: Transaction Publishers, 2005 [4] Medioni G, Tang C K. Tensor Voting: Theory and Applications [EB/OL]. [2000-12-01]. http://www.wisdom.weizmann.ac.id/~boiman/reading/tensor_voting./teasor_voting.pdf [5] Wang S, Kubota T, Siskind J M. Salient Boundary Detection Using Ratio Contour // Proc of the 17 Annual Conference on Neural Information Processing Systems. Whistler, Canada, 2003: 1571-1578 [6] Wang Song, Kubota T, Siskind J, et al. Salient Closed Boundary Extraction with Ratio Contour. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(4): 546-561 [7] Chalmond B, Francesconi B, Herbin S. Using Hidden Scale for Salient Object Detection. IEEE Trans on Image Processing, 2006,15(9): 2644-2656 [8] Liu Tie, Sun Jian, Zheng Nanning, et al. Learning to Detect a Salient Object // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Minneapolis, USA, 2007: 1-8 [9] Achanta R, Estrada F, Wils P, et al. Salient Region Detection and Segmentation // Proc of the 6th International Conference on Computer Vision Systems. Santorini, Greece, 2008: 66-75 [10] Shi Jianbo, Malik J. Normalized Cuts and Image Segmentation. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905 [11] Castleman K R. Digital Image Processing. Upper Saddle River, USA: Prentice Hall, 1996 [12] Ojala T, Pietikinen M, Harwood D. A Comparative Study of Texture Measures with Classification Based on Feature Distributions. Pattern Recognition, 1996, 29(1): 51-59 [13] Wang Tao, Hu Shimin, Sun Jiaguang. Image Retrieval Based on Color-Spatial Feature. Journal of Software, 2002, 13(10): 2031-2036 (in Chinese) (王 涛,胡事民,孙家广.基于颜色-空间特征的图像检索.软件学报, 2002, 13(10): 2031-2036) [14] Elder J H, Zucker S W. Computing Contour Closure // Proc of the 4th European Conference on Computer Vision. Cambridge, UK, 1996: 399-412 [15] Dijkstra E W. A Note on Two Problems in Connection with Graphs. Numerische Mathematik, 1959, 1(1): 269-271
2010, Vol. 23 
