Remote sensing image classification and recognition based on KFCM

Author

Shi Yun-song ; Shi Yu-feng

Author_Institution

Coll. of Civil Eng., Nanjing Forestry Univ., Nanjing, China

fYear

2010

fDate

24-27 Aug. 2010

Firstpage

1062

Lastpage

1065

Abstract

Based on fuzzy C-means method and the characteristics of kernel-based method, the algorithm of kernel-based fuzzy clustering is presented, in which the objective function of fuzzy C-means is substituted by Gaussian kernel objective function. The approach of kernel-based fuzzy C-means clustering is used in the classification and recognition of remote sensing images, and the result shows that it can effectively improve the classification accuracy of remote sensing images compared with the traditional fuzzy C-means clustering.

Keywords

Gaussian processes; fuzzy set theory; geophysical image processing; image classification; pattern clustering; remote sensing; Gaussian kernel objective function; KFCM; classification accuracy; fuzzy c-means method; image recognition; kernel-based fuzzy c-means clustering; kernel-based method; remote sensing image classification; Accuracy; Algorithm design and analysis; Buildings; Classification algorithms; Clustering algorithms; Kernel; Remote sensing; classification and recognition; clustering; fuzzy C-means; kernel fuzzy C-means; remote sensing image;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Education (ICCSE), 2010 5th International Conference on

Conference_Location

Hefei

Print_ISBN

978-1-4244-6002-1

Type

conf

DOI

10.1109/ICCSE.2010.5593412

Filename

5593412