Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (20): 65-67.

• 学术探讨 • Previous Articles     Next Articles

Algorithm of wavelet-based multiresolution image fusion

PU Xi-long,LV Jian-ping   

  1. Department of Electronic and Information College,Suzhou University,Suzhou,Jiangsu 215021,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-07-11 Published:2007-07-11
  • Contact: PU Xi-long



  1. 苏州大学 电子信息学院,江苏 苏州 215021
  • 通讯作者: 浦西龙

Abstract: The image fusion is the process of combining two or more images into a single image.Fused image retains important features from each.Image fusion techniques can improve the quality,and increase the application of these data.The paper mostly addresses two issues in image fusion:(1)the image fusion algorithm;(2)corresponding quality assessment.In the image fusion scheme presented in this paper,the original images are preprocessed by multiresolution wavelet transforms first,then the wavelet transforms coefficients of the input images are appropriately selected by certain fusion rules,and the new image is obtained by taking the inverse wavelet transform of the fused wavelet coefficients.Quality assessment for fused images is also discussed in this paper.

Key words: image fusion, multiresolution analysis, wavelet transform, quality assessment

摘要: 图像的融合过程是将两个或更多的图像结合成一个图像,融合图像保留了每一个图像的重要特征。图像融合技术能够提高图像质量和数据的实用性。主要描述了图像融合的两个课题:(1)融合算法;(2)质量评估。介绍的图像融合算法是先对原图像进行多分辨小波变换,再把输入图像的小波变换系数通过一定的融合规则进行选择,然后经过逆小波变换得到新的图像,对图像融合的质量评估也进行了讨论。

关键词: 图像融合, 多分辨分析, 小波变换, 质量评估