A multiscale representation including opponent color features for texture recognition
- 1 January 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 7 (1) , 124-128
- https://doi.org/10.1109/83.650858
Abstract
We introduce a representation for color texture using unichrome and opponent features computed from Gabor filter outputs. The unichrome features are computed from the spectral bands independently while the opponent features combine information across different spectral bands at different scales. Opponent features are motivated by color opponent mechanisms in human vision. We present a method for efficiently implementing these filters, which is of particular interest for processing the additional information present in color images. Using a data base of 2560 image regions, we show that the multiscale approach using opponent features provides better recognition accuracy than other approaches.Keywords
This publication has 11 references indexed in Scilit:
- Texture features for browsing and retrieval of image dataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Retrieving multispectral satellite images using physics-based invariant representationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Illumination-invariant recognition of texture in color imagesJournal of the Optical Society of America A, 1995
- Markov random field models for unsupervised segmentation of textured color imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- Use of invariants for recognition of three-dimensional color texturesJournal of the Optical Society of America A, 1994
- Efficient computation of gabor filter based multiresolution responsesPattern Recognition, 1994
- Unsupervised texture segmentation using Gabor filtersPattern Recognition, 1991
- Multichannel texture analysis using localized spatial filtersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filtersJournal of the Optical Society of America A, 1985
- An opponent-process theory of color vision.Psychological Review, 1957