电子学报 ›› 2013, Vol. 41 ›› Issue (1): 199-204.DOI: 10.3969/j.issn.0372-2112.2013.01.034

• 科研通信 • 上一篇    

基于自适应局部Log-Gabor能量的多聚焦图像融合

卢振坤1,2, 玉振明1   

  1. 1. 梧州学院信号处理实验室,广西梧州 543002;
    2. 华南理工大学电子与信息学院,广东广州 510641
  • 收稿日期:2012-02-14 修回日期:2012-08-01 出版日期:2013-01-25
    • 作者简介:
    • 卢振坤 男,博士研究生,1979年生于广西百色.梧州学院副教授,目前在华南理工大学电子与信息学院攻读博士学位.研究方向为数字图像处理、非平稳信号处理. E-mail:lzk06@sina.com 玉振明 男,博士后,1963年出生于广西藤县.梧州学院教授.主要研究方向:图像信息处理、电机控制. E-mail:yumingming@vip.sina.com
    • 基金资助:
    • 国家自然科学基金 (No.61062014); 广西自然科学基金 (No.2010GXNSFB013056); 广西科技开发项目 (No.11107007-4); 广西教育厅科研项目 (No.201106LX555); 梧州市科技开发项目 (No.201101049)

Multi-Focus Image Fusion Based on Adaptive Localized Log-Gabor Energy

LU Zhen-kun1,2, YU Zhen-ming1   

  1. 1. Signal Processing Laboratory, Wuzhou University, Wuzhou, Guangxi 543002, China;
    2. School of Electronic and Information Engineering, South China University of Technology, Guangzhou, Guangdong 510640, China
  • Received:2012-02-14 Revised:2012-08-01 Online:2013-01-25 Published:2013-01-25
    • Supported by:
    • National Natural Science Foundation of China (No.61062014); Natural Science Foundation of Guangxi Zhuang Autonomous Region,  China (No.2010GXNSFB013056); Guangxi Science and Technology Development Project (No.11107007-4); Research Project of Guangxi Education Department (No.201106LX555); Wuzhou Science and Technology Development Project (No.201101049)

摘要: 利用全局搜索策略,设计适用于图像融合的最佳Log-Gabor滤波器组,并提出了一种基于自适应局部Log-Gabor能量的多聚焦图像融合方法:首先将多聚焦图像进行自适应分块,然后用最佳Log-Gabor滤波器组对这些子图像进行滤波,从而提取出该子图像的Log-Gabor能量,比较对应子图像的Log-Gabor能量,以挑选出其中清晰的像素并进行一致性检验,重构图像.本文给出了融合实验结果和各项评价指标,结果表明该方法与经典的融合方法相比性能更优,明显提高融合图像质量和运行效率.

关键词: 图像融合, Log-Gabor滤波器, Log-Gabor能量, 自适应分块

Abstract: A method for multi-focus image fusion based on adaptive localized Log-Gabor energy is proposed.The best Log-Gabor filter banks for image fusion are designed by the global search strategy.Multi-focus image is adaptively divided into some sub-blocks.Sub-image is filtered by the best Log-Gabor filter banks for extracting Log-Gabor energy of the sub-image.The clear pixels of image are picked out by comparing corresponding the Log-Gabor energy of sub-image,then the consistency is checked.Finally,image is reconstructed.Experimental results show that the proposed method provides superior performance over conventional fusion methods in improving the quality of fused images and the operational efficiency.

Key words: image fusion, Log-Gabor filters, Log-Gabor energy, adaptive partitioning

中图分类号: