Contour and texture analysis for image segmentation

被引:718
作者
Malik, J [1 ]
Belongie, S [1 ]
Leung, T [1 ]
Shi, JB [1 ]
机构
[1] Univ Calif Berkeley, Div Comp Sci, Berkeley, CA 94720 USA
基金
美国国家科学基金会;
关键词
segmentation; texture; grouping; cue integration; texton; normalized cut;
D O I
10.1023/A:1011174803800
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture. Natural images contain both textured and untextured regions, so the cues of contour and texture differences are exploited simultaneously. Contours are treated in the intervening contour framework, while texture is analyzed using textons. Each of these cues has a domain of applicability, so to facilitate cue combination we introduce a gating operator based on the texturedness of the neighborhood at a pixel. Having obtained a local measure of how likely two nearby pixels are to belong to the same region, we use the spectral graph theoretic framework of normalized cuts to find partitions of the image into regions of coherent texture and brightness. Experimental results on a wide range of images are shown.
引用
收藏
页码:7 / 27
页数:21
相关论文
共 40 条
[1]  
[Anonymous], 1985, GM RES LABS TECHN PU
[2]  
Belongie S., 1998, Computer Vision - ECCV'98. 5th European Conference on Computer Vision. Proceedings, P751, DOI 10.1007/BFb0055702
[3]   Color- and texture-based image segmentation using EM and its application to content-based image retrieval [J].
Belongie, S ;
Carson, C ;
Greenspan, H ;
Malik, J .
SIXTH INTERNATIONAL CONFERENCE ON COMPUTER VISION, 1998, :675-682
[4]   INFERRING SURFACES FROM IMAGES [J].
BINFORD, TO .
ARTIFICIAL INTELLIGENCE, 1981, 17 (1-3) :205-244
[5]  
CANNY JF, 1986, PAMI, V8, P6, DOI DOI 10.1109/TPAMI.1986.4767851
[6]  
Chung F, 1997, C BOARD MATH SCI AM
[7]  
DeValois R.L., 1988, Spatial vision
[8]  
ELDER JH, 1996, P 4 EUR C COMP VIS, V1, P399
[9]  
FOGEL I, 1989, BIOL CYBERN, V61, P103, DOI 10.1007/BF00204594
[10]   STOCHASTIC RELAXATION, GIBBS DISTRIBUTIONS, AND THE BAYESIAN RESTORATION OF IMAGES [J].
GEMAN, S ;
GEMAN, D .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (06) :721-741