The selection of local dynamic threshold based on niched genetic algorithm

Author

Chen, Xi ; Yang, Jie

Author_Institution

Wuhan Univ. of Technol., Wuhan

Volume

3

fYear

2007

fDate

2-4 Nov. 2007

Firstpage

967

Lastpage

970

Abstract

In this paper, one improved algorithm for the selection of local dynamic threshold based on niched genetic algorithm is proposed. With the maximum variance method being used as the fitness evaluation function, the genetic algorithm is designed, putting the image segmentation problem into one of the optimization issue. The optimal threshold is searched from the all segmentation parameter space by experiencing the global exploring ability of the genetic algorithm. Compared with some problems of simple genetic algorithm, these are amended by the niche idea. The results of experiment show that the proposed method has better robust performance.

Keywords

genetic algorithms; image segmentation; probability; fitness evaluation function; genetic algorithm; image segmentation; local dynamic threshold; maximum variance; optimal threshold; segmentation parameter space; Algorithm design and analysis; Background noise; Entropy; Genetic algorithms; Image segmentation; Notice of Violation; Pattern analysis; Pattern recognition; Real time systems; Wavelet analysis; Image segmentation; genetic algorithm; local dynamic threshold; maximum variance; niche;

fLanguage

English

Publisher

ieee

Conference_Titel

Wavelet Analysis and Pattern Recognition, 2007. ICWAPR '07. International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-1065-1

Electronic_ISBN

978-1-4244-1066-8

Type

conf

DOI

10.1109/ICWAPR.2007.4421570

Filename

4421570