[1]王书朋,蒋 艺.基于鲁棒主成分分析的多聚焦图像融合[J].计算机技术与发展,2020,30(10):53-58.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 010]
　WANG Shu-peng,JIANG Yi.Multi-focus Image Fusion Based on Robust Principal Component Analysis[J].,2020,30(10):53-58.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 010]
点击复制

基于鲁棒主成分分析的多聚焦图像融合()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年10期
页码:
53-58
栏目:
智能、算法、系统工程
出版日期:
2020-10-10

文章信息/Info

Title:
Multi-focus Image Fusion Based on Robust Principal Component Analysis
文章编号:
1673-629X(2020)10-0053-06
作者:
王书朋; 蒋 艺
西安科技大学 通信与信息工程学院,陕西 西安 710054
Author(s):
WANG Shu-peng; JIANG Yi
School of Communication and Information Engineering,Xi’an University of Science and Technology,Xi’an 710054,China
关键词:
多聚焦图像; 图像融合; 鲁棒主成分分析; 卷积神经网络; 融合规则
Keywords:
multi-focus image; image fusion; robust principle component analysis; convolutional neural network; fusion rule
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 10. 010
摘要:
针对多聚焦图像融合提取聚焦区域不准确,融合图像的边缘存在伪影的问题,提出了一种基于鲁棒主成分分析的多聚焦图像融合方法。首先,用鲁棒主成分分析将源图像分解为低秩分量和稀疏分量。 然后分析不同分量的特性,设计相应的融合规则。 针对低秩分量,提出基于卷积神经网络的融合策略,用于提取源图像的纹理细节,构建权重图;对于稀疏分量,采用基于拉普拉斯能量和的方法生成决策图,为了使决策图的边缘与源图像保持一致,将多幅源图像的均值作为引导图像并用引导滤波器对决策图进行优化。 最后,根据融合后的低秩分量和稀疏分量重构出最终的融合图像。 实验结果表明,该方法提高了融合图像的对比度和边缘清晰度,在主观分析和客观评价指标上都优于其他七种方法。
Abstract:
In order to solve the problems of inaccurate focusing region extraction and artifacts in edge of image fusion,we propose a new image fusion algorithm based on robust principal component analysis. Firstly, the source images are decomposed into low-rank components and spare components by robust principal component analysis. Then the characteristics of different components is analyzed and the corresponding fusion rules are designed. For the low-rank components,a fusion rule based on convolutional neural network is proposed to extract the texture details of the source image and construct the weight map. For the sparse components,the Sum-ModifiedLaplacian is used to generate the decision map. In order to keep the boundary of the decision map consistent with the source images,the mean value of multiple source images is used as the guided image in the guided filter to optimize the decision map. Finally,the final fused image is reconstructed from the fused low-rank component and the sparse component. The experiment shows that the proposed method improves the contrast and edge definition of the fused images,and is superior to other seven methods in both subjective and objective evaluation indicators.

相似文献/References:

[1]冉柯柯 王继成.基于比值法图像拼接的等比例改进算法[J].计算机技术与发展,2010,(02):5.
　RAN Ke-ke,WANG Ji-cheng.An Improved Mosaic Algorithm Based on Ratio Matching Using Geometric Proportion[J].,2010,(10):5.
[2]焦晶萍 廖文和 沈建新.一种基于模板匹配法的眼底图像拼接方法[J].计算机技术与发展,2010,(04):148.
　JIAO Jing-ping,LIAO Wen-he,SHEN Jian-xin.A Fundus Image Mosaic Method Based on Template Matching[J].,2010,(10):148.
[3]玄立超 谢亦才.一种新的基于Curvelet变换的遥感图像融合算法[J].计算机技术与发展,2009,(05):119.
　XUAN Li-chao,XIE Yi-cai.A New Remote Sensing Image Fusion Algorithm Based on Curvelet Transform[J].,2009,(10):119.
[4]田闯 刘文波.基于Curvelet变换多聚焦图像融合[J].计算机技术与发展,2008,(07):29.
　TIAN Chuang,LIU Wen-bo.Multifocus Image Fusion Using Curvelet Transform[J].,2008,(10):29.
[5]杨晓慧 朱秀阁.基于非下采样Contourlets的CT／MRI图像自适应融合[J].计算机技术与发展,2008,(12):116.
　YANG Xiao-hui,ZHU Xiu-ge.Adaptive CT/MRI Image Fusion Based on Nonsubsampled Contourlets[J].,2008,(10):116.
[6]刘凯峰 张德祥.基于小波变换区域方差的遥感图像融合新算法[J].计算机技术与发展,2007,(05):177.
　LIU Kai-feng,ZHANG De-xiang.A New Fusion Algorithm of Remote Sensing Image Based on Local Deviation of Wavelet Transform[J].,2007,(10):177.
[7]舒坚 胡茂林.空间频率图像的智能融合[J].计算机技术与发展,2006,(03):37.
　SHU Jian,HU Mao-lin.Intelligent Fusion of Image in Spatial Frequency[J].,2006,(10):37.
[8]魏世超 段先华 夏加星.基于Sobel算子和局部能量的图像融合新算法[J].计算机技术与发展,2012,(04):61.
　WEI Shi-chao,DUAN Xian-hua,XIA Jia-xing.Novel Image Fusion Algorithm Based on Sobel Operator and Region Energy[J].,2012,(10):61.
[9]王福田 吴福虎 罗斌 汤进.基于相位相关的电力红外热像拼接[J].计算机技术与发展,2012,(05):150.
　WANG Fu-tian,WU Fu-hu,LUO Bin.Infrared Image Mosaicing in Power System Based on Phase Correlation[J].,2012,(10):150.
[10]江铁,朱桂斌,孙奥.基于金字塔变换的多曝光图像融合[J].计算机技术与发展,2013,(01):95.
　JIANG Te,ZHU Gui-bin,SUN Ao.Multi-exposure Image Fusion Based on Pyramid Transformation[J].,2013,(10):95.
[11]杨亚 王铮 张素兰 郭飞飞.基于小波变换的多聚焦图像融合[J].计算机技术与发展,2010,(03):56.
　YANG Ya,WANG Zheng,ZHANG Su-lan,et al.Multi - focus Image Fusion Scheme Based on Wavelet Transform[J].,2010,(10):56.
[12]冯太平 闫仁武.基于非抽样Contourlet变换的多聚焦图像融合算法[J].计算机技术与发展,2012,(02):57.
　FENG Tai-ping,YAN Ren-wu.Multi-Focus Image Fusion Algorithm Based on Nonsubsampled Contourlet Transform[J].,2012,(10):57.
[13]刘 佳,李登峰.特征匹配度结合边缘检测的图像融合技术[J].计算机技术与发展,2020,30(09):43.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 008]
　LIU Jia,LI Deng-feng.Image Fusion Technology Based on Feature Matching and Edge Detection[J].,2020,30(10):43.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 008]
[14]王 程,王 巍,杨 馨,等.基于区域特征优化及边缘增强的多聚焦图像融合[J].计算机技术与发展,2024,34(04):62.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 010]
　WANG Cheng,WANG Wei,YANG Xin,et al.Multi-focus Image Fusion Based on Feature Optimization of Region and Edge Enhancement[J].,2024,34(10):62.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 010]

更新日期/Last Update: 2020-10-10