作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (10): 220-221,. doi: 10.3969/j.issn.1000-3428.2007.10.079

• 人工智能及识别技术 • 上一篇    下一篇

基于独立分量分析的图像融合算法

吴 强1,王行愚2   

  1. (1. 驻511厂军代表室,南京 210002;2. 华东理工大学信息科学与工程学院,上海 200237)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-05-20 发布日期:2007-05-20

Image Fusion Algorithm Based on Independent Component Analysis

WU Qiang1, WANG Xingyu2   

  1. (1. No.511 Factory of the PLA, Nanjing 210002; 2. School of Information Science and Engineering, ECUST, Shanghai 200237)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-05-20 Published:2007-05-20

摘要: 提出了一种基于独立分量分析(ICA)的图像融合算法。在图像配准的基础上,利用独立分量分析对图像进行训练获得独立分量基函数。对于待融合图像,通过训练得到的基函数对图像进行线性变换,然后在变换域根据不同的融合规则对图像进行融合,ICA反变换得到融合图像。仿真结果表明了该方法的有效性。
关键词:

关键词: 图像融合, 独立分量分析, 融合规则

Abstract: A novel image fusion algorithm based on independent component analysis is proposed. Suppose the images have been registered, the independent component analysis bases are obtained by offline training images with the same texture. The images are fused in the ICA transformed domain by different fusion rules. The result is got by inverse ICA transform. Experimental results demonstrate the effectiveness of the method.

Key words: Image fusion, Independent component analysis, Fusion rules

中图分类号: