A Selective Attention Computational Model for Perceiving Textures

Authors:
Woobeom Lee
Affiliations:
School of Computer&Information Engineering, Sangji University, Republic of Korea 220-702
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
Year:
2008

Citing 4
Cited 0

Multichannel Texture Analysis Using Localized Spatial Filters

IEEE Transactions on Pattern Analysis and Machine Intelligence
Rotation invariant texture classification using even symmetric Gabor filters

Pattern Recognition Letters
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information

Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Texture segmentation by unsupervised learning and histogram analysis using boundary tracing

CIS'05 Proceedings of the 2005 international conference on Computational Intelligence and Security - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a biologically-inspired method of perceiving textures from various texture images. Our approach is motivated by a computational model of neuron cells found in the cerebral visual cortex. An unsupervised learning schemes of SOM(: Self-Organizing Map) is used for the block-based textures clustering, plus a selective attention computational model tuning to the response frequency properties of texture is used for perceiving any texture from the clustered texture. To evaluate the effectiveness of the proposed method, various texture images were built, and the quality of the perceived TROI(: Texture Region Of Interest) was measured according to the discrepancies. Our experimental results demonstrated a very successful performance.