Rotation invariant texture recognition using a steerable pyramid

Author

Greenspan, H. ; Belongie, S. ; Goodman, R. ; Perona, P.

Author_Institution

California Inst. of Technol., Pasadena, CA, USA

Volume

2

fYear

1994

fDate

9-13 Oct 1994

Firstpage

162

Abstract

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

Keywords

image texture; DFT-encoding step; backpropagation classifiers; filter set; input rotation angle estimation; input textures; invariant representation; k-nearest-neighbours classifiers; representative feature extraction; rotation-invariant texture recognition; rule-based classifiers; steerable oriented pyramid; supervised classification; Band pass filters; Data mining; Degradation; Discrete Fourier transforms; Feature extraction; Image databases; Image recognition; Laplace equations; Marine vehicles; Spatial databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1994. Vol. 2 - Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on

Conference_Location

Jerusalem

Print_ISBN

0-8186-6270-0

Type

conf

DOI

10.1109/ICPR.1994.576896

Filename

576896