Separating color and pattern information for color texture discrimination
- 25 June 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (10514651) , 668-671
- https://doi.org/10.1109/icpr.2002.1044840
Abstract
The analysis of colored surface textures is a challenging research problem in computer vision. Current approaches to this task can be roughly divided into two categories: methods that process color and texture information separately and those that utilize multispectral texture descriptions. Motivated by recent psychophysical findings, we find the former approach quite auspicious. We propose the use of complementary color and texture measures that are combined on a higher level, and empirically demonstrate the validity of our proposition using a large set of natural color textures.Keywords
This publication has 14 references indexed in Scilit:
- Outex - new framework for empirical evaluation of texture analysis algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Pattern—color separable pathways predict sensitivity to simple colored patternsVision Research, 1996
- Texture features for browsing and retrieval of image dataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Accurate color discrimination with classification based on feature distributionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Markov random field models for unsupervised segmentation of textured color imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- On the classification of image regions by colour, texture and shapePattern Recognition, 1993
- Color indexingInternational Journal of Computer Vision, 1991
- Concurrent processing streams in monkey visual cortexTrends in Neurosciences, 1988
- Multispectral TextureIEEE Transactions on Systems, Man, and Cybernetics, 1982