Contour and texture analysis for image segmentation
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Contour and texture analysis for image segmentation. / Malik, Jitendra; Belongie, Serge; Leung, Thomas; Shi, Jianbo.
In: International Journal of Computer Vision, Vol. 43, No. 1, 06.2001, p. 7-27.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Contour and texture analysis for image segmentation
AU - Malik, Jitendra
AU - Belongie, Serge
AU - Leung, Thomas
AU - Shi, Jianbo
N1 - Funding Information: The authors would like to thank the Berkeley vision group, especially Chad Carson, Alyosha Efros, David Forsyth, and Yair Weiss for useful discussions during the development of the algorithm. We thank Doron Tal for implementing the algorithm in C++. This research was supported by (ARO) DAAH04-96-1-0341, the Digital Library Grant IRI-9411334, NSF Graduate Fellowships to SB and JS and a Berkeley Fellowship to TL.
PY - 2001/6
Y1 - 2001/6
N2 - 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.
AB - 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.
KW - Cue integration
KW - Grouping
KW - Normalized cut
KW - Segmentation
KW - Texton
KW - Texture
UR - http://www.scopus.com/inward/record.url?scp=0035358181&partnerID=8YFLogxK
U2 - 10.1023/A:1011174803800
DO - 10.1023/A:1011174803800
M3 - Journal article
AN - SCOPUS:0035358181
VL - 43
SP - 7
EP - 27
JO - International Journal of Computer Vision
JF - International Journal of Computer Vision
SN - 0920-5691
IS - 1
ER -
ID: 302058963