基于纹理和梯度特征的多尺度图像融合方法

被引:3
作者
程全 [1 ,2 ]
马军勇 [3 ,4 ]
机构
[1] 郑州大学信息工程学院
[2] 周口师范学院物理与机电工程学院
[3] 光电控制技术重点实验室
[4] 中航工业洛阳电光设备研究所
关键词
纹理特征; 梯度特征; 图像融合;
D O I
10.16511/j.cnki.qhdxxb.2014.07.017
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
该文提出一种基于纹理和梯度特征的多尺度图像融合方法。采用纹理提取滤波器和边缘梯度滤波器模板分别对每层Gauss金字塔进行滤波,生成多尺度纹理和边缘图像,使得多分辨率变换域中能够将原图像中的纹理信息包含进来,从而为进一步融合提供更全面的信息量度。采用该文所提出的方法对红外与可见光图像进行融合仿真,并且与具有代表性的融合方法进行了比较。实验结果与图像融合质量评价显示了该文所提出方法的优越性。
引用
收藏
页码:935 / 941
页数:7
相关论文
共 10 条
[1]  
Matching Images to Models for Registration and Object Detection via Clustering. Stockman G,Kopstein S,Benett S. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1982
[2]  
Enhanced image capture through fusion. Burt P J,Kolczynski R J. Proceedings of the 4th International Conferenceon Computer Vision . 1993
[3]  
Information measure for performance of image fusion. Qu, Guihong,Zhang, Dali,Yan, Pingfan. Electronics Letters . 2002
[4]  
The laplacian pyramid as a compact image code. Burt PJ,Adelson EH. IEEE Transactions on Communications . 1983
[5]  
Image fusion through consideration of texture components. Barron, D.R.,Thomas, O.D.J. Electronics Letters . 2001
[6]  
Cross-band pixel selection in multiresolution image fusion. Petrovic V,Xydeas C. Proceedings of SPIE the International Society for Optical Engineering . 1999
[7]  
Feature-based fusion of infrared and visible dynamic images using target detection[J]. 刘从义,敬忠良,肖刚,杨波.  Chinese Optics Letters. 2007(05)
[8]   Efficient algorithms for robust feature matching [J].
Mount, DM ;
Netanyahu, NS ;
Le Moigne, J .
PATTERN RECOGNITION, 1999, 32 (01) :17-38
[9]  
Categorization of multiscale-decomposition-based image fusion schemes with a performance study for a digital camera application. Zhang, Zhong,Blum, Rick S. Proceedings of Tricomm . 1999
[10]  
Multisensor image fusion:Concept,method and application. Wang Y N,Lohmann B. . 2000