J4 ›› 2015, Vol. 32 ›› Issue (5): 539-549.

• Image and Information Proc. • Previous Articles     Next Articles

Design of improved hyperspectral image classification scheme based on weighted fuzzy C means algorithm  

Ma Huan, Jing Zhiyong,Chen Ming,Zhang Jianwei   

  1. Software Engineering College, Zhengzhou University of Light Industry, Zhengzhou 450001, China
  • Received:2015-02-06 Revised:2015-05-22 Published:2015-09-28 Online:2015-09-28

Abstract:

In order to improve the classification accuracy of hyperspectral image data, reduce dependence on large number of data sets.An improved method based on weighted fuzzy C means algorithm is proposed for feature extraction of hyperspectral data in this paper,. The approach is an extension of previous approach—prototype space feature extraction. Each feature with different weights in terms of weighted fuzzy c means algorithm to ensure the features contain more information after extracted. Experiments results show that compared to results obtained from approach prototype spatial feature extraction method , this method has a stability to data set and higher classification accuracy when extracted a small number of features used to hyperspectral image data classification.

Key words: hyperspectral image, data classification, feature extraction, weighted fuzzy c-means