Multiple channel neural network model for texture classification and segmentation

Author

Leung, M. ; Peterson, A.M.

Author_Institution

Dept. of Electr. Eng., Stanford Univ., CA, USA

fYear

1991

fDate

14-17 Apr 1991

Firstpage

2677

Abstract

A computational image analysis model that resembles the functioning of the brain is introduced. The multiple-channel neural network model consists of three stages: multiple-channel representation, neural network classification and spatial context correction. The model is implemented and applied to the problem of texture analysis. Gabor filters are involved to represent the textural patterns. Low misclassification rates are obtained. Composite textural images are also applied to the system and accurately segmented images are obtained. The usefulness of the model is demonstrated

Keywords

computerised pattern recognition; computerised picture processing; neural nets; Gabor filters; computational image analysis model; multiple-channel neural network model; multiple-channel representation; neural network classification; segmentation; spatial context correction; texture classification; Artificial neural networks; Biological neural networks; Computational modeling; Context modeling; Gabor filters; Image processing; Image segmentation; Image texture analysis; Management training; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on

Conference_Location

Toronto, Ont.

ISSN

1520-6149

Print_ISBN

0-7803-0003-3

Type

conf

DOI

10.1109/ICASSP.1991.150953

Filename

150953