21 September 2001 Using opponent correlation functions to recognize color texture
Author Affiliations +
Proceedings Volume 4550, Image Extraction, Segmentation, and Recognition; (2001) https://doi.org/10.1117/12.441465
Event: Multispectral Image Processing and Pattern Recognition, 2001, Wuhan, China
Abstract
We propose a new approach to model texture in 2D color images based on opponent correlation functions computed within and between sensor bands of a red-green-blue image. The new opponent correlations cover all the possible opponent autocorrelations and opponent crosscorrelations of a color image. Invariants of opponent correlations are computed with the aid of Zernike moments to preserve rotation, translation, and scale invariance. The method can be used in the classification (even with slight illumination changes) and the unsupervised segmentation of color texture in a variety of image processing and pattern recognition tasks. One of the most important points in introducing the opponent correlation functions is the efficient computation compared to the direct spatial correlation method that requires heavy computations.
© (2001) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mohammed Al-Rawi, Mohammed Al-Rawi, Jie Yang, Jie Yang, } "Using opponent correlation functions to recognize color texture", Proc. SPIE 4550, Image Extraction, Segmentation, and Recognition, (21 September 2001); doi: 10.1117/12.441465; https://doi.org/10.1117/12.441465
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

Algebraic relational approach to conflating images
Proceedings of SPIE (September 23 2003)
Eigen indexing in satellite recognition
Proceedings of SPIE (August 24 1999)
Multiscale object-oriented change detection over urban areas
Proceedings of SPIE (October 28 2006)
Data mining within digital images
Proceedings of SPIE (April 25 2007)

Back to Top