Rotation invariant texture recognition using a steerable pyramid
- 17 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 162-167
- https://doi.org/10.1109/icpr.1994.576896
Abstract
A rotation-invariant texture recognition system is pre- sented. A steerable orientedpyramid is used to extract rep- resentative features for the input textures. The steerability of the filter set allows a ship to an invariant representation via a DFT-encoding step. Supervised classijkation follows. State-of-the-art recognition results are presented on a 30 texture database with a comparison across the performance of the K-nn, Back-Propagation and Rule-Based classifiers. In addition, high accuracy estimation of the input rotation angle is demonstrated.Keywords
This publication has 11 references indexed in Scilit:
- Learning texture discrimination rules in a multiresolution systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Overcomplete steerable pyramid filters and rotation invariancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Texture classification by wavelet packet signaturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Rule-Based Neural Networks for Classification and Probability EstimationNeural Computation, 1992
- Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiersIEEE Transactions on Neural Networks, 1992
- Classification of rotated and scaled textured images using Gaussian Markov random field modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Unsupervised texture segmentation using Gabor filtersPattern Recognition, 1991
- A Model-Based Method for Rotation Invariant Texture ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- Sum and Difference Histograms for Texture ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- Texture Analysis Using Generalized Co-Occurrence MatricesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1979