Share Email Print
cover

Proceedings Paper

On the optimal choice of parameters in using fuzzy clustering algorithm for segmentation of plant disease leaf images
Author(s): Yancheng Zhang; Hanping Mao; Yongguang Hu; Bo Hu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

As an important classifier, fuzzy c-means clustering technique has been widely used in segmentation of image. It is an adaptive segmentation method for plant disease images. However, it has some uncertain factors, when it is used for specific segmentation problem, that are input parameters value. The input parameters include the feature of the date set, the optimal number of cluster, and the degree of fuzziness. These parameters affect the speed and precision of fuzzy clustering segmentation. In this paper, the optimal choice of parameters in a fuzzy c-means algorithm for segmentation of plant disease image was discussed and investigated. Using the pixels gray and means of neighborhood pixels as input feature data; an adapting the FCM algorithm parameters based on fuzzy partition entropy, fuzzy partition coefficient, and compactness measures was used to choose the optimal cluster number; and experiments was used for choosing the degree of fuzziness. The Results show that the optimal clustering number for disease leaf segmentation problem is 4 and the degree of fuzziness is 2.

Paper Details

Date Published: 11 December 2006
PDF: 7 pages
Proc. SPIE 6411, Agriculture and Hydrology Applications of Remote Sensing, 641119 (11 December 2006); doi: 10.1117/12.697754
Show Author Affiliations
Yancheng Zhang, Jiangsu Univ. (China)
Yunnan Agricultural Univ. (China)
Hanping Mao, Jiangsu Univ. (China)
Yongguang Hu, Jiangsu Univ. (China)
Bo Hu, Jiangsu Univ. (China)


Published in SPIE Proceedings Vol. 6411:
Agriculture and Hydrology Applications of Remote Sensing
Robert J. Kuligowski; Jai S. Parihar; Genya Saito, Editor(s)

© SPIE. Terms of Use
Back to Top