计算机工程

• 图形图像处理 • 上一篇    下一篇

基于稀疏表示的遥感图像分类方法改进

唐晓晴,刘亚洲,陈骏龙   

  1. (南京理工大学计算机科学与工程学院,南京 210094)
  • 收稿日期:2015-01-04 出版日期:2016-03-15 发布日期:2016-03-15
  • 作者简介:唐晓晴(1990-),女,硕士研究生,主研方向为图像处理、模式识别;刘亚洲,讲师、博士;陈骏龙,硕士研究生。

Improvement of Remote Sensing Image Classification Method Based on Sparse Representation

TANG Xiaoqing,LIU Yazhou,CHEN Junlong   

  1. (School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China)
  • Received:2015-01-04 Online:2016-03-15 Published:2016-03-15

摘要:

传统稀疏表示分类算法由于没有给出全面的图像纹理信息,导致分类准确率不高。针对该问题,在稀疏表示分类模型中引入局部二值模式(LBP)特征,提出一种新的稀疏表示分类方法。该方法使用LBP对遥感图像进行特征提取,获得遥感图像的局部纹理特征,根据LBP直方图训练结构化字典,建立基于稀疏表示的遥感图像分类模型。实验结果表明,与支持向量机以及K最近邻方法相比,该方法能够有效提高分类精度。

关键词: 稀疏表示, 局部二值模式, 遥感图像, 局部纹理, 字典学习

Abstract:

Owing to the traditional Sparse Representation-based Classification(SRC) algorithm can not extract image texture information comprehensively,the result of classification is not high.In order to solve this problem,the Local Binary Pattern(LBP) feature is added to the SRC model,and a novel sparse representation classification method is proposed.The LBP is used to extract the local texture of the remote sensing image and the LBP histogram is used to design a structured dictionary,which is more suitable for the remote sensing image.Compared with the Support Vector Machine(SVM) and K-nearest Neighbor(KNN) method,experimental results show that the proposed method can improve the classification accuracy.

Key words: sparse representation, Local Binary Pattern(LBP), remote sensing image, local texture, dictionary learning

中图分类号: