A self-organizing neural network for image segmentation

Author

Kong, H. ; Guan, L.

Author_Institution

Dept. of Electr. Eng., Sydney Univ., NSW, Australia

fYear

1994

fDate

29 Nov-2 Dec 1994

Firstpage

27

Lastpage

31

Abstract

A new method is proposed for multiscale image segmentation. The method is based on pixel classification by means of a self organizing neural network. The core concept of this processing method is to explicitly treat segmentation as a classification problem. An unsupervised learning algorithm is utilized in the processing. Compared with other segmentation methods, the proposed one has a number of desirable features. It is self adaptive, efficient, and easy to control. The effectiveness of the proposed method is verified through several experiments

Keywords

image classification; image segmentation; self-organising feature maps; unsupervised learning; classification problem; image segmentation; multiscale image segmentation; pixel classification; self organizing neural network; self-organizing neural network; unsupervised learning algorithm; Automatic control; Image color analysis; Image resolution; Image segmentation; Image texture analysis; Neural networks; Supervised learning; Unsupervised learning; Visualization; Volume measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Information Systems,1994. Proceedings of the 1994 Second Australian and New Zealand Conference on

Conference_Location

Brisbane, Qld.

Print_ISBN

0-7803-2404-8

Type

conf

DOI

10.1109/ANZIIS.1994.396956

Filename

396956