Rotation invariant texture recognition using a steerable pyramid

A rotation-invariant texture recognition system is presented. A steerable oriented pyramid is used to extract representative features for the input textures. The steerability of the filter set allows a shift to an invariant representation via a DFT-encoding step. Supervised classification follows. S...

Full description

Saved in:
Bibliographic Details
Main Authors: Greenspan, H., Belongie, S., Goodman, R., Perona, P.
Format: Conference Proceeding
Language:English
Subjects:
Band pass filters
Data mining
Degradation
Discrete Fourier transforms
Feature extraction
Image databases
Image recognition
Laplace equations
Marine vehicles
Spatial databases
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A rotation-invariant texture recognition system is presented. A steerable oriented pyramid is used to extract representative features for the input textures. The steerability of the filter set allows a shift to an invariant representation via a DFT-encoding step. Supervised classification follows. State-of-the-art recognition results are presented on a 30 texture database with a comparison across the performance of the k-NN, backpropagation and rule-based classifiers. In addition, high accuracy estimation of the input rotation angle is demonstrated.
ISSN:1051-4651
DOI:10.1109/ICPR.1994.576896