Detection of Earth Surface Cracks Using Parallel Genetic Algorithm Based Thresholding

Author

Kanungo, P. ; Nanda, P.K. ; Ghosh, A.

Author_Institution

Dept. of E&TC, C.V. Raman Coll. of Eng., Bhubaneswar, India

fYear

2009

fDate

28-29 Dec. 2009

Firstpage

4

Lastpage

11

Abstract

A parallel genetic algorithm (PGA) based scheme for detection of cracks in images is proposed. The proposed segmentation scheme is a feature based one and the optimum threshold is determined from the the feature histogram. Parallel genetic algorithm (PGA) based clustering is proposed to detect two peaks and thereafter the optimal threshold is determined by minimum mean square error (MMSE) based strategy. The proposed method has been tested successfully with various images. The performance of the proposed method is compared with that of Otsu´s, Kwon´s, feature less(FL) and feature based(FB) approaches and it is found that the proposed method outperformed all these methods for crack detection.

Keywords

Earth; feature extraction; genetic algorithms; image segmentation; least mean squares methods; parallel algorithms; clustering; earth surface cracks; feature histogram; feature-based method; featureless method; image segmentation; minimum mean square error-based strategy; parallel genetic algorithm based thresholding; Concurrent computing; Earth; Electronics packaging; Genetic algorithms; Histograms; Image segmentation; Least squares approximation; Pixel; Surface cracks; Telecommunication computing; Clustering; Image Segmentation; Parallel Genetic Algorithm; Thresholding;

fLanguage

English

Publisher

ieee

Conference_Titel

Advances in Computing, Control, & Telecommunication Technologies, 2009. ACT '09. International Conference on

Conference_Location

Trivandrum, Kerala

Print_ISBN

978-1-4244-5321-4

Electronic_ISBN

978-0-7695-3915-7

Type

conf

DOI

10.1109/ACT.2009.12

Filename

5376896