Comparison of texture features based on Gabor filters
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The performance of a number of texture feature operators is evaluated. The features are all based on the local spectrum which is obtained by a bank of Gabor filters. The comparison is made using a quantitative method which is based on Fisher's criterion. It is shown that, in general, the discrimination effectiveness of the features increases with the amount of post-Gabor processing.Keywords
This publication has 18 references indexed in Scilit:
- Nonlinear operator for oriented textureIEEE Transactions on Image Processing, 1999
- Texture edge detection by modelling visual cortical channelsPattern Recognition, 1995
- Symmetry Interpretation of Complex Moments and the Local Power SpectrumJournal of Visual Communication and Image Representation, 1995
- Hierarchical image segmentation by multi-dimensional clustering and orientation-adaptive boundary refinementPattern Recognition, 1995
- N-folded symmetries by complex moments in Gabor space and their application to unsupervised texture segmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- Unsupervised texture segmentation using Gabor filtersPattern Recognition, 1991
- Preattentive texture discrimination with early vision mechanismsJournal of the Optical Society of America A, 1990
- Multichannel texture analysis using localized spatial filtersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Complex-cell receptive field modelsProgress in Neurobiology, 1988
- 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