Modeling and Classifying Symmetries Using a Multiscale Opponent Color Representation

Authors:
Bea Thai;Glenn Healey
Affiliations:
Univ. of California, Irvine;Univ. of California, Irvine
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1998

Citing 6
Cited 7

On Image Analysis by the Methods of Moments

IEEE Transactions on Pattern Analysis and Machine Intelligence
N-folded Symmetries by Complex Moments in Gabor Space and their Application to Unsupervised Texture Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Illumination-Invariant Recognition of 3D Objects Using Local Color Invariants

IEEE Transactions on Pattern Analysis and Machine Intelligence
Radiometric CCD camera calibration and noise estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Markov Random Field Models for Unsupervised Segmentation of Textured Color Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Color Angular Indexing

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II

Color texture measurement and segmentation

Signal Processing - Special section on content-based image and video retrieval
Comparative experiment with colour texture classifiers using the CCR feature space

Pattern Recognition Letters
Using phase information for symmetry detection

Pattern Recognition Letters
Recognition of coloured and textured images through a multi-scale neural architecture with orientational filtering and chromatic diffusion

Neurocomputing
Fourier fractal descriptors for colored texture analysis

ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
An appearance-based approach to assistive identity inference using LBP and colour histograms

ACCV'10 Proceedings of the 2010 international conference on Computer vision - Volume Part I
Illuminant invariant descriptors for color texture classification

CCIW'13 Proceedings of the 4th international conference on Computational Color Imaging

Quantified Score

Hi-index	0.14

Visualization

Abstract

A new class of multiscale symmetry features provides a useful high-level representation for color texture. These symmetry features are defined within and between the bands of a color image using complex moments computed from the output of a bank of orientation and scale selective filters. We show that these features not only represent symmetry information but are also invariant to rotation, scale, and illumination conditions. The features computed between color bands are motivated by opponent process mechanisms in human vision. Experimental results are provided to show the performance of this set of features for texture classification and retrieval.