›› 2011, Vol. 24 ›› Issue (11): 66-.

• Articles • Previous Articles     Next Articles

A Method of SAR Image Texture Feature Extraction Based on Co-occurrence Matrix

 YANG Kai-Zhi, CHENG Ying-Lei   

  1. (School of Telecommunications Engineering,Air Force Engineering University,Xi'an 710077,China)
  • Online:2011-11-15 Published:2011-11-25

Abstract:

To extract available information from SAR images effectively,this paper proposes a method of texture feature extraction based on co-occurrence matrix.This paper first analyzes the common attribute values of co-occurrence matrix and the influence of window size and displacement vector on texture feature.By comparing the distribution and mean value of different objects' texture,it obtains the best window size and displace vector used to calculate co-occurrence matrix,and determines practicable texture feature combination for classification.Finally,this paper gives methods for texture feature selection and extraction.The experiment results show that the features extracted by the method are effective in describing objects.

Key words: SAR image;texture feature;co-occurrence matrix;feature extraction

CLC Number: 

  • TN958