Rotation invariant texture recognition using a steerable pyramid

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

doi:10.1109/ICPR.1994.576896

Rotation invariant texture recognition using a steerable pyramid

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

Department of Bio-Medical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

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.

Original language	Undefined/Unknown
Title of host publication	Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5)
Pages	162-167
Volume	3
DOIs	https://doi.org/10.1109/ICPR.1994.576896
State	Published - 1 Oct 1994

Keywords

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

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICPR.1994.576896

Cite this

@inproceedings{578a67d3654244f7ac504b2f67456268,

title = "Rotation invariant texture recognition using a steerable pyramid",

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

author = "H. Greenspan and S. Belongie and R. Goodman and P. Perona",

year = "1994",

month = oct,

day = "1",

doi = "10.1109/ICPR.1994.576896",

language = "???core.languages.und???",

isbn = "0-8186-6270-0",

volume = "3",

pages = "162--167 ",

booktitle = "Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5)",

}

Rotation invariant texture recognition using a steerable pyramid. / Greenspan, H.; Belongie, S.; Goodman, R. et al.
Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5). Vol. 3 1994. p. 162-167 .

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Rotation invariant texture recognition using a steerable pyramid

AU - Greenspan, H.

AU - Belongie, S.

AU - Goodman, R.

AU - Perona, P.

PY - 1994/10/1

Y1 - 1994/10/1

N2 - 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.

AB - 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.

KW - image texture

KW - rotation-invariant texture recognition

KW - steerable oriented pyramid

KW - representative feature extraction

KW - input textures

KW - filter set

KW - invariant representation

KW - DFT-encoding step

KW - supervised classification

KW - k-nearest-neighbours classifiers

KW - backpropagation classifiers

KW - rule-based classifiers

KW - input rotation angle estimation

KW - Image databases

KW - Feature extraction

KW - Spatial databases

KW - Discrete Fourier transforms

KW - Laplace equations

KW - Band pass filters

KW - Marine vehicles

KW - Image recognition

KW - Data mining

KW - Degradation

U2 - 10.1109/ICPR.1994.576896

DO - 10.1109/ICPR.1994.576896

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

SN - 0-8186-6270-0

VL - 3

SP - 162

EP - 167

BT - Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5)

ER -