• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 图形与图像 • 上一篇    下一篇

基于增补小波变换和PCNN的NSCT域图像融合算法

王健1,2,张修飞1,任萍1,院文乐1   

  1. (1.西北工业大学电子信息学院,陕西 西安 710129;2.西北工业大学第365研究所,陕西 西安 710065)
  • 收稿日期:2017-06-27 修回日期:2017-11-09 出版日期:2018-10-25 发布日期:2018-10-25
  • 基金资助:

    国家自然科学基金(61472324);西北工业大学研究生创意创新种子基金(Z2017144)

An image fusion algorithm based on complementary
wavelet transform and PCNN in NSCT domain

WANG Jian1,2,ZHANG Xiufei1,REN Ping1,YUAN Wenle1   

  1. (1.School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710129;
    2.No.365 Institute,Northwestern Polytechnical University,Xi’an 710065,China)

     
  • Received:2017-06-27 Revised:2017-11-09 Online:2018-10-25 Published:2018-10-25

摘要:

针对传统NSCT图像融合算法存在的不足,提出一种基于增补小波变换和PCNN的NSCT域图像融合算法。首先对源图像进行NSCT分解,生成一系列低频和高频分量。对低频分量利用二维小波分解,生成一个低频和三个方向分量,对低频分量利用局部区域能量加权方法融合,三个方向分量利用改进的高斯加权SML方法融合;对NSCT分解的高频分量,分为对最高层和其它层的融合,最高层利用改进的高斯加权SML方法融合,其余层利用边缘梯度信息激励PCNN方法融合。最后对NSCT进行逆变换得到融合图像。实验结果证实了所提算法的有效性。

 

关键词: 图像融合, NSCT, 小波变换, PCNN, SML

Abstract:

Aiming at the shortcomings of the traditional NSCT image fusion algorithm, we propose an image fusion algorithm based on complementary wavelet transform and PCNN in NSCT domain. Firstly, we use the NSCT to decompose the source image and generate a series of low frequency and high frequency subbands. Low frequency subbands are decomposed by twodimensional wavelet into a low frequency subband and three directional subbands. Then the low frequency subband is fused by the local region energy weighting method. And the three directional subbands are fused by the improved Gaussian weighted SML method. The high frequency subbands decomposed by the NSCT are divided into the highest layers and other layers for fusion. The highest layers are fused by using the improved Gaussian weighted SML method, and the other layers are fused by the PCNN method enhanced by edge gradient information. Finally, the fused image is obtained through NSCT inverse transform. Experimental results demonstrate the effectiveness of the proposed algorithm.
 

Key words: image fusion, NSCT, wavelet transform, PCNN, SML