Edge Segmentation Based on Automatic Scale Selection

Abstract

Abstract:

This paper presented a novel method to select the edge scale automatically, which could be used to split complicated interleaving edges into more meaningful edge segments that could be classified easily according to their features. First, edge extreme paths in Gaussian scale space were searched to obtain the characteristic scale for each edge point, by calculating the maximum distance the edge point travels from one scale level to adjacent one and analyzing the four forms of extreme path evolution. Then, interleaving edges were split into pieces with different scales according to their scale histogram. These edge pieces connecting with each other were combined through extreme path in scale space. Experimental results show that the proposed method is effective in edge segmentation based on characteristic scales and saliency of edge.

Key words：

Key words: edge segmentation, characteristic scale, extreme path, multi-scale representation

CLC Number:

TP 311

XIANG Ke,WANG Xuanyin,CAO Songxiao. Edge Segmentation Based on Automatic Scale Selection[J]. Journal of Shanghai Jiaotong University, 2013, 47(12): 1888-1895.

References

［1］Arbelaez P, Marie M, Fowlkes C, et al. From contours

to regions: An empirical evaluation［C］// IEEE Conference on Computer Vision and Pattern Recognition. Miami, Florida: IEEE Press, 2009: 22942301.

［2］Arbelaez P, Marie M, Fowlkes C, et al. Contour detection and hierarchical image segmentation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5): 898916.

［3］Dollar P, Tu Z W, Belongie S. Supervised learning of edges and object boundaries［C］// IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE Press, 2006: 19641971.

［4］Barinova O, Lempitsky V, Kholi P. On detection of multiple object instances using hough transforms［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(9): 17731784.

［5］Wang H Z, Oliensis J. Generalizing edge detection to contour detection for image segmentation［J］. Computer Vision and Image Understanding, 2010, 114(7): 731744.

［6］Mishra A K, Fieguth P W, Clausi D A. Decoupled active contour (DAC) for boundary detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(2): 310324.

［7］AlDiri B, Hunter A, Steel D. An active contour model for segmenting and measure retinal vessels［J］. IEEE Transactions on Medical Imaging, 2009, 28(9): 14881497.

［8］Coleman S A, Scotney B W, Suganthan S. Multiscale edge detection on range and intensity images［J］. Pattern Recognition, 2011, 44(4): 821838.

［9］Ren X F. Multiscale improves boundary detection in natural images［C］// 10th European Conference on Computer Vision. Marseille, France: Springer, 2008: 533545.

［10］Sumengen B, Manjunath B S, Kenney C. Image segmentation using curve evolution and flow fields［C］// 16th International Conference on Pattern Recognition. Quebe c, Canada: IEEE Press, 2002: 105108.

[1]	HU Xiaoqiang,ZHONG Xunyu,ZHANG Xiaoli,PENG Xiafu,HE Ying. A Two-Level Fault Diagnosis Method for Gyro-Quadruplet Assisted by Support Vector Machine [J]. Journal of Shanghai Jiaotong University, 2020, 54(11): 1151-1156.
[2]	JIN Yi,ZHANG Sulan,LI Shuang,SHEN Yunfu,OUYANG Shan,PENG Junjie. The Computing-Data File: A Key Technology of Applying Ternary Optical Computer [J]. Journal of Shanghai Jiaotong University, 2019, 53(5): 584-592.
[3]	WANG Zheng,CHU Xuening,CHEN Hansi,ZHANG Lei,YAN Bo1,LIU Hang. A Method for Prediction of Smartphone Performance Requirements and Perception Analysis Based on Operating Data [J]. Journal of Shanghai Jiaotong University, 2018, 52(7): 777-783.
[4]	TAN Mingchaoa,DIAO Xingchuna,CAO Jianjuna,FENG Jingb. An Attribute Similarity Adjusting Algorithm Based on Functional Dependency [J]. Journal of Shanghai Jiaotong University, 2015, 49(08): 1075-1083.
[5]	LU Chengbo，MEI Ying. An Accurate and Robust Online Sequential Learning Algorithm for Feedforward Networks [J]. Journal of Shanghai Jiaotong University, 2015, 49(08): 1137-1143.
[6]	CHEN Shuang1,2,3,SONG Jinyu1,DIAO Xingchun1,2,CAO Jianjun2. Estimation of Enumerative Missing Values Based on Relational Markov Model [J]. Journal of Shanghai Jiaotong University, 2013, 47(08): 1246-1250.
[7]	ZHANG Jian-Bo, ZHOU Si-Bo, YUAN Guo-Bin, SHI Yang, ZHU Jian-Bo. Parallel Processing Mapping Strategy of Spatial Analysis under the Heterogeneous Environment [J]. Journal of Shanghai Jiaotong University, 2013, 47(01): 70-75.
[8]	LIU Hai-Tao-a, WEI Ru-Xiang-b, JIANG Guo-Ping-a. Similarity Measurement of Software Cost Data [J]. Journal of Shanghai Jiaotong University, 2012, 46(11): 1736-1740.
[9]	ZHANG Qingyuan1,PAN Li1,ZI Xiaochao2. A Shared Congestion Detection Technique Based on Weighted First Order LocalRegion Method [J]. Journal of Shanghai Jiaotong University, 2010, 44(02): 287-0291.
[10]	ZHAO Yanli,JIANG Zhibin,LI Na. Modeling of Clinical Pathway Based on Hierarchical Timed Colored Petri Net [J]. Journal of Shanghai Jiaotong University, 2010, 44(02): 252-0258.
[11]	TENG Long-mei1,2，LIU Ren-yi2，LIU Nan2. Study on Integrated Management of Marine Remote Sensing Data [J]. Journal of Shanghai Jiaotong University, 2008, 42(10): 1674-1677.
[12]	ZHENG Yang,CHEN Haibo,ZANG Binyu. Snooping-Based Distributed Shared Memory [J]. Journal of Shanghai Jiaotong University, 2018, 52(10): 1333-1338.