计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (6): 169-170.DOI: 10.3778/j.issn.1002-8331.2010.06.049

• 图形、图像、模式识别 • 上一篇    下一篇

基于多小波变换的多聚焦图像融合

朱四荣,王迎春   

  1. 武汉理工大学 理学院,武汉 430070
  • 收稿日期:2008-08-28 修回日期:2008-10-30 出版日期:2010-02-21 发布日期:2010-02-21
  • 通讯作者: 朱四荣

Multi-focus image fusion method based on multi-wavelet transform

ZHU Si-rong,WANG Ying-chun   

  1. School of Sciences,Wuhan University of Technology,Wuhan 430070,China
  • Received:2008-08-28 Revised:2008-10-30 Online:2010-02-21 Published:2010-02-21
  • Contact: ZHU Si-rong

摘要: 多聚焦图像融合的关键问题是如何保持原始图像的边缘和细节信息。多小波分析具有多个分析基函数和产生更多分解子图像的特点。在多小波变换域对低频和高频小波系数采用不同的融合方法——对低频系数采用取平均的方法,而对高频系数采用边缘梯度对比的方法。通过实验证明,该方法能够很好地保存图像的边缘和细节信息,融合结果得到了改善。

关键词: 多小波变换, 边缘梯度, 图像融合

Abstract: The key problem in multi-focus image fusion is how to keep the detail and edge in the original image.Based on the features of more decomposing sub-images generated by the multi-wavelet analysis function,a new image fusion method is proposed in this paper.In wavelet domain,different fusion rules are adopted for low frequency coefficient and high frequency coefficient.The rule of average method is used to fuse low frequency coefficient and the contrast of edge gradient for high frequency coefficient.The experiments demonstrate that this method can save the edge of original image and improve the result.

Key words: multi-wavelet, edge gradient, image fusion

中图分类号: