Back to Search
Start Over
[Untitled]
- Source :
- International Journal of Computer Vision. 43:7-27
- Publication Year :
- 2001
- Publisher :
- Springer Science and Business Media LLC, 2001.
-
Abstract
- 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.
- Subjects :
- Texture compression
Pixel
business.industry
Texton
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Pattern recognition
Image segmentation
Grayscale
Texture (geology)
Computer Science::Graphics
Image texture
Artificial Intelligence
Texture filtering
Computer Science::Computer Vision and Pattern Recognition
Computer vision
Computer Vision and Pattern Recognition
Artificial intelligence
business
Software
ComputingMethodologies_COMPUTERGRAPHICS
Mathematics
Subjects
Details
- ISSN :
- 09205691
- Volume :
- 43
- Database :
- OpenAIRE
- Journal :
- International Journal of Computer Vision
- Accession number :
- edsair.doi...........87e8ac3573ad079567c836ab2a7ff28a