基于图像抠图技术的多聚焦图像融合方法

doi:10.11772/j.issn.1001-9081.2016.07.1949

计算机应用 ›› 2016, Vol. 36 ›› Issue (7): 1949-1953.DOI: 10.11772/j.issn.1001-9081.2016.07.1949

基于图像抠图技术的多聚焦图像融合方法

张盛林, 易本顺, 李卫中, 刘红玉

武汉大学电子信息学院, 武汉 430072

收稿日期:2015-12-08 修回日期:2016-02-23 出版日期:2016-07-10 发布日期:2016-07-14
通讯作者: 易本顺
作者简介:张盛林(1989-),男,湖南张家界人,硕士研究生,主要研究方向:图像融合;易本顺(1965-),男,湖北武汉人,教授,博士生导师,博士,主要研究方向:多媒体网络通信;李卫中(1983-),男,湖北孝感人,博士研究生,主要研究方向:图像融合;刘红玉(1990-),女,湖北麻城人,硕士研究生,主要研究方向:语音、图像处理。

Multi-focus image fusion method based on image matting technique

ZHANG Shenglin, YI Benshun, LI Weizhong, LIU Hongyu

School of Electronic Information, Wuhan University, Wuhan Hubei 30072, China

Received:2015-12-08 Revised:2016-02-23 Online:2016-07-10 Published:2016-07-14

摘要/Abstract

摘要： 针对多聚焦图像融合容易出现信息丢失、块效应明显等问题，提出了一种新的基于图像抠图技术的多聚焦图像融合算法。首先，通过聚焦检测获得源图像的聚焦信息，并根据所有源图像的聚焦信息生成融合图像的三分图，即前景、背景和未知区域；然后，利用图像抠图技术，根据三分图获得每一幅源图像的精确聚焦区域；最后，将这些聚焦区域结合起来构成融合图像的前景和背景，并根据抠图算法得到的确定前景、背景对未知区域进行最优融合，增强融合图像前景、背景与未知区域相邻像素之间的联系，实现图像融合。实验结果表明，与传统算法相比，所提算法在客观评价方面能获得更高的互信息量（MI）和边缘保持度，在主观评价方面能有效抑制块明显效应，得到更优的视觉效果。该算法可以应用到目标识别、计算机视觉等领域，以期得到更优的融合效果。

关键词: 多聚焦图像, 聚焦信息, 三分图, 图像抠图, 图像融合

Abstract: To solve the problem of information loss and obvious block effect in multi-focus image fusion, a novel multi-focus image fusion method based on image matting technique was proposed. Firstly, the rough focus information of each source image was obtained by focusing measure, all of which was used to generate the trimap of the fusion image, namely, foreground, background and unknown region. Secondly, according to the trimap, the precise focus region of each source image could be gotten by using the image matting. Finally, the obtained focus regions were combined to consist of new foreground and background. And the optimal fusion of the unknown region was conducted on the basis of the foreground and background, which enhanced the correlations between the nearby pixels of the three focusing regions. The experimental results show that compared with the traditional algorithms, the proposed algorithm can acquire higher Mutual Information (MI) and edge preservation on the objective evaluation. For the subjective evaluation, it can be seen that the block effect is obviously suppressed and the visual effect is more excellent. The proposed algorithm can be applied to the object identification and computer vision to obtain optimal fusion result.

Key words: multi-focus image, focus information, trimap, image matting, image fusion

中图分类号:

TP391.413

张盛林, 易本顺, 李卫中, 刘红玉. 基于图像抠图技术的多聚焦图像融合方法[J]. 计算机应用, 2016, 36(7): 1949-1953.

ZHANG Shenglin, YI Benshun, LI Weizhong, LIU Hongyu. Multi-focus image fusion method based on image matting technique[J]. Journal of Computer Applications, 2016, 36(7): 1949-1953.

参考文献

[1] 张亚秋.多聚焦图像融合算法研究[D].重庆:重庆大学,2014:8-9.(ZHANG Y Q. Research on multi-focus image fusion[D]. Chongqing:Chongqing University, 2014:8-9)
[2] 欧阳宁,邹宁,张彤,等.基于非下采样Shearlet变换与聚焦区域检测的多聚焦图像融合算法[J].计算机应用,2015,35(2):490-494.(OUYANG N, ZOU N, ZHANG T, et al. Multi-focus image fusion algorithm based on nonsubsampled Shearlet transform and focused regions detection[J]. Journal of Computer Applications, 2015, 35(2):490-494.)
[3] WANG W, CHANG F. A multi-focus image fusion method based on Laplacian pyramid[J]. Journal of Computers, 2011, 6(12):2559-2566.
[4] PAJARES G, DE LA CRUZ J M. A wavelet-based image fusion tutorial[J]. Pattern Recognition, 2004, 37(9):1855-1872.
[5] 范艳玲,杨明.基于双树复小波变换的多聚焦图像融合[J].核电子学与探测技术,2014,34(2):204-207.(FAN Y L, YANG M. Multi-focus image fusion based on dual-tree complex wavelet transform[J]. Nuclear Electronics and Detection Technology, 2014, 34(2):204-207.)
[6] 马苗,万仁远,尹义龙.基于相似性灰关联的Curvelet域多聚焦图像融合[J].电子学报,2012,40(10):1984-1988.(MA M, WAN R Y, YIN Y L. Multi-focus image fusion based on grey relation of similarity in curvelet domain[J]. Acta Electronica Sinica, 2012, 40(10):1984-1988.)
[7] LI H, CHAI Y, LI Z. Multi-focus image fusion based on nonsubsampled contourlet transform and focused regions detection[J]. Optik-International Journal for Light and Electron Optics, 2013, 124(1):40-51.
[8] 石智,张卓,岳彦刚.基于Shearlet变换的自适应图像融合算法[J].光子学报,2013,42(1):115-120.(SHI Z, ZHANG Z, YUE Y G. Adaptive image fusion algorithm based on Sheartlet transform[J]. Acta Photonica Sinica, 2013, 42(1):115-120)
[9] 彭真明,景亮,何艳敏,等.基于多尺度稀疏字典的多聚焦图像超分辨融合[J].光学精密工程,2014,22(1):169-176.(PENG Z M, JING L, HE Y M, et al. Superresolution fusion multi-focus image based on multiscale sparse dictionary[J]. Optics and Precision Engineering, 2014, 22(1):169-176.)
[10] 逄浩辰,朱明,郭立强.彩色图像融合客观评价指标[D].北京:中国科学院大学,2014:14-23.(PANG H C, ZHU M, GUO L Q. Objective color image fusion performance index[D]. Beijing:University of Chinese Academy of Sciences, 2014:14-23.)
[11] 李卓婷.三种典型数字图像抠图方法的比较[D].广州:华南理工大学,2013:49-51.(LI Z T. Applications of quaternion in skeleton skin technology[D]. Guangzhou:South China University of Technology, 2013:49-51)
[12] PORTER T, DUFF T. Compositing digital images[J]. ACM SIGGRAPH Computer Graphics, 1984, 18(3):253-259.
[13] GRADY L. Random walks for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(11):1768-1783.
[14] WANG J, COHEN M F. Optimized color sampling for robust matting[C]//CVPR'07:Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2007:1-8.
[15] HUANG W, JING Z. Evaluation of focus measures in multi-focus image fusion[J]. Pattern Recognition Letters, 2007, 28(4):493-500.
[16] 左雷,王炜,张鑫.基于像素邻域SML的多焦距图像融合方法[J].微计算机信息,2010,26(35):221-222.(ZUO L, WANG W, ZHANG X. Enhanced multi-focus image fusion based on sum modified Laplacian in pixel neighborhood[J]. Microcomputer Information, 2010, 26(35):221-222.)
[17] QU G, ZHANG D, YAN P. Information measure for performance of image fusion[J]. Electronics Letters, 2002, 38(7):313-315.
[18] PETROVI V, XYDEAS C. Objective evaluation of signal-level image fusion performance[J]. Optical Engineering, 2005, 44(8):087003-1-087003-8.
[19] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.

基于图像抠图技术的多聚焦图像融合方法

Multi-focus image fusion method based on image matting technique

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	张林发, 张榆锋, 王琨, 李支尧. 基于直觉模糊集和亮度增强的医学图像融合[J]. 计算机应用, 2021, 41(7): 2082-2091.
[2]	牛康力, 谌雨章, 沈君凤, 曾张帆, 潘永才, 王绎冲. 基于深度学习的双通道夜视图像复原方法[J]. 计算机应用, 2021, 41(6): 1775-1784.
[3]	吴蕾, 杨晓敏. 改进的基于通道注意力反馈网络的遥感图像融合算法[J]. 计算机应用, 2021, 41(4): 1172-1178.
[4]	黄思远, 张敏情, 柯彦, 毕新亮. 基于显著性检测的图像隐写分析方法[J]. 计算机应用, 2021, 41(2): 441-448.
[5]	成亚玲, 柏智, 谭爱平. 基于引导滤波和差分图像的多聚焦图像融合方法[J]. 计算机应用, 2021, 41(1): 220-224.
[6]	李卫中. 基于场景局部特征的多曝光图像融合[J]. 计算机应用, 2020, 40(8): 2365-2371.
[7]	王继霄, 李阳, 王家宝, 苗壮, 张洋硕. 基于SqueezeNet的轻量级图像融合方法[J]. 计算机应用, 2020, 40(3): 837-841.
[8]	刘颖, 王凤伟, 刘卫华, 艾达, 李芸, 杨凡超. 基于亮度分区模糊融合的高动态范围成像算法[J]. 计算机应用, 2020, 40(1): 233-238.
[9]	王书朋, 赵瑶. 基于自适应分割的多曝光图像融合算法[J]. 计算机应用, 2020, 40(1): 252-257.
[10]	牟琦, 唐洋, 李占利, 李洪安. 基于网格运动统计算法和最佳缝合线的密集重复结构图像快速拼接方法[J]. 计算机应用, 2020, 40(1): 239-244.
[11]	张斌, 罗晓清, 张战成. 基于TV-L¹结构纹理分解的图像融合质量评价算法[J]. 计算机应用, 2019, 39(9): 2701-2706.
[12]	王克强, 张雨帅, 王保群. 基于Retinex理论的多曝光图像融合算法[J]. 计算机应用, 2019, 39(7): 2087-2092.
[13]	吴宗骏, 吴炜, 杨晓敏, 刘凯, Gwanggil Jeon, 袁皓. 改进的基于稀疏表示的全色锐化算法[J]. 计算机应用, 2019, 39(2): 540-545.
[14]	刘斌, 辛迦楠, 谌文江, 肖惠勇. 不可分拉普拉斯金字塔构造及其在多光谱图像融合中的应用[J]. 计算机应用, 2019, 39(2): 564-570.
[15]	高媛, 吴帆, 秦品乐, 王丽芳. 生成对抗残差网络的医学图像融合算法[J]. 计算机应用, 2019, 39(12): 3528-3534.