自然图像对的联合抠图方法

doi:10.16182/j.issn1004731x.joss.201811016

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (11): 4180-4186.doi: 10.16182/j.issn1004731x.joss.201811016

自然图像对的联合抠图方法

魏毅¹, 商柳², 邱嘉和², 张桂娟³, 朱登明^{2,4, *}, 沈燕飞⁵

1. 武夷学院数学与计算机学院,武夷山 354300;
2. 中国科学院计算技术研究所,北京 100190;
3. 山东师范大学信息科学与工程学院,济南 250014;
4. 太仓中科信息技术研究院,太仓 215400;
5. 北京体育大学信息工程学院,北京 100084

收稿日期:2018-05-05 修回日期:2018-06-10 发布日期:2019-01-04
第一作者简介:魏毅(1978-),男,福建建瓯,博士,讲师,研究方向为虚拟现实。
基金资助:
国家科技重大专项(2017ZX05019005),国家自然科学基金(61173067, 61379085, 61572299), 国家863计划(2015AA016401),福建省自然科学基金项目(2018J01562)

Co-matting of Natural Image Pairs

Wei Yi¹, Shang Liu², Qiu Jiahe², Zhang Guijuan³, Zhu Dengming^{2,4, *}, Shen Yanfei⁵

1. School of Mathematics and Computer, Wuyi University, Wuyishan 354300, China;
2. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China;
3. School of Information Science and Engineering, Shandong Normal University, Jinan 250014, China;
4. Taicang Institute of Information Technology, Taicang 215400, China;
5. School of Information Engineering, Beijing Sport University, Beijing 100084, China

Received:2018-05-05 Revised:2018-06-10 Published:2019-01-04

摘要/Abstract

摘要： 针对自然图像的抠图问题,研究了一种基于闭形式解的图像对联合抠图方法。根据输入的两张图像与其初始掩像,计算图像对之间的相似矩阵;扩展现有描述单幅图像的抠图拉普拉斯矩阵,提出一种联合抠图拉普拉斯矩阵来刻画图像对;基于联合抠图拉普拉斯矩阵构造能量函数,并通过求解其极小值得到图像对的抠图结果。在多个数据集上进行了实验,实验结果表明新方法具有很好的抠图效果,适用于连续图像序列的抠图。

关键词: 自然图像抠图, 联合抠图, 相似性估计, 联合抠图拉普拉斯

Abstract: Aiming at dealing with the problem of natural image matting, this study focused on a closed-form solution to image pairs matting. For given two images and their corresponding trimaps, the affinity matrix between the two images is calculated. The matting Laplacian which characters an image to co-matting Laplacian which characters a pair of images is generalized. The alpha mattes of image pairs were obtained by optimizing the energy function which derived from co-matting Laplacian. To validate the approach, the experiments on several datasets are conducted. The results demonstrate that the method can achieve higher quality and is suitable for matting of a sequence of images.

Key words: natural image matting, co-matting, affinity estimation, co-matting Laplacian

中图分类号:

TP391.9

魏毅,商柳,邱嘉和等 . 自然图像对的联合抠图方法[J]. 系统仿真学报, 2018, 30(11): 4180-4186.

Wei Yi,Shang Liu,Qiu Jiahe,et al . Co-matting of Natural Image Pairs[J]. Journal of System Simulation, 2018, 30(11): 4180-4186.

参考文献

[1] 沈洋, 林晓, 谢志峰, 等. 交互式前景抠图技术综述[J]. 计算机辅助设计与图形学学报, 2014, 26(4): 511-519.
Shen Yang, Lin Xiao, Xie Zhifeng, et al.A survey on interactive alpha matting technology[J]. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(4): 511-519.
[2] Porter T, Duff T.Compositing digital images[C]//Proc of the 11th Annual Conference on Computer Graphics and Interactive Techniques. New York: ACM Press, 1984: 253-259.
[3] Chuang Y Y, Curless B, Salesin D H, et al.A Bayesian approach to digital matting[C]//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Kauai: IEEE Computer Society Press, 2001: 264-271.
[4] Guan Y, Chen W, Liang X, et al.Easy matting-a stroke based approach for continuous image matting[J]. Computer Graphics Forum (S1467-8659), 2006, 25(3): 567-576.
[5] Shahrian E, Rajan D, Price B.Improving image matting using comprehensive sampling sets[C]//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Portland: IEEE Computer Society Press, 2013: 636-643.
[6] Levent K, Aykut, E, Erkut E. Alpha matting with KL-divergence-based sparse sampling[J]. IEEE Transactions on Image Processing (S1057-7149), 2017, 26(9): 4523-4536.
[7] Jubin J, Ehsan S V, Hisham C, et al.Sparse coding for alpha matting[J]. IEEE Transactions on Image Processing (S1057-7149), 2016, 25(7): 3032-3043.
[8] Sun J, Jia J, Tang C K, et al.Poisson matting[J]. ACM Transactions on Graphics (S1557-7368), 2004, 23(3): 315-321.
[9] Grady L, Schiwietz T, Aharon S, et al.Random walks for interactive alpha-matting[C]//Proc of Visualization, Im-aging, and Image Processing. Benidorm: ACTA Press, 2005: 423-429.
[10] Levin A, Lischinski D, Weiss Y.A closed-form solution to natural image matting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2008, 30(2): 228-242.
[11] Wang J, Cohen M F.Optimized color sampling for robust matting[C]//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Minnesota: IEEE Computer Society Press, 2007: 1-8.
[12] He K, Rhemann C, Rother C, et al.A global sampling method for alpha matting[C]//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Colorado: IEEE Computer Society Press, 2011: 2049-2056.
[13] Jin M, Kim B, Song W.Adaptive propagation-based color sampling for alpha matting[J]. IEEE Transactions on Circuits and Systems for Video Technology (S1051-8215), 2014, 24(7): 1101-1110.
[14] Rother C, Minka T, Blake A, et al.Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFS[C]// Proc of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE Computer Society Press, 2006: 993-1000.
[15] Sun J, Li Y, Kang S B, et al.Flash matting[J]. ACM Transactions on Graphics (S1557-7368), 2006, 25(3): 772-778.
[16] Wang L, Xia T, Guo Y, et al.Confidence-driven image co-matting[J]. Computers & Graphics (S0097-8493), 2014, 38(1): 131-139.
[17] Koen E A, Theo G, Cees G M.Evaluating color descriptors for object and scene recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-882 8), 2010, 32(9): 1582-1596.
[18] Rhemann C, Rother C, Wang J, et al. Alpha matting evaluation website[DB/OL]. [2018-05-05]. http://www.alphamatting. com
[19] Batra D, Kowdle A, Parikh D, et al.iCoseg: interactive co-segmentation with intelligent scribble guidance[C]// Proc of the IEEE Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE Computer Society Press, 2010: 3169-3176.
[20] Ning Xu, Brian Price, Scott Cohen, et al.Deep Image Matting[C]//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE Computer Society Press, 2017: 311-320.

自然图像对的联合抠图方法

Co-matting of Natural Image Pairs

PDF (PC)

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

本文评价

[1]	黄涛, 张智, 丁玉杰, 陈艳波, 王晶, 张文倩. 考虑动态频率安全与N-k故障的鲁棒应急调度方法[J]. 系统仿真学报, 2025, 37(12): 2981-2993.
[2]	张润昭, 陈艳波, 黄涛, 田昊欣, 强涂奔, 张智. 基于异构负荷特征解析预测的虚拟电厂调度方法[J]. 系统仿真学报, 2025, 37(12): 2994-3006.
[3]	于祥星, 赵艳东, 张宝琳. 基于电涡流NES的海上风机塔架振动控制[J]. 系统仿真学报, 2025, 37(12): 3007-3017.
[4]	李斌, 王于绰. 基于多策略融合的光伏系统故障诊断方法[J]. 系统仿真学报, 2025, 37(12): 3018-3032.
[5]	李孝斌, 胡冰, 尹超, 李波, 马军. 基于时空图卷积的汽车配件供应链需求预测与仿真分析[J]. 系统仿真学报, 2025, 37(12): 3060-3074.
[6]	彭艺, 雷云揆, 杨青青, 李辉, 王健明. 改进PID搜索算法的山地环境无人机路径规划[J]. 系统仿真学报, 2025, 37(12): 3075-3086.
[7]	陈逸, 邱思航, 朱正秋, 季雅泰, 赵勇, 鞠儒生. 基于启发式的人-大模型协作寻源方法[J]. 系统仿真学报, 2025, 37(12): 3112-3127.
[8]	索婧怡, 卢柏宏, 屈澈. 影视LED光源光强分布测定及其在游戏引擎中的仿真研究[J]. 系统仿真学报, 2025, 37(12): 3140-3151.
[9]	龚建兴, 胡海, 任海慧, 吴瑞祥. 面向虚实结合的军事训练系统互操作模型与运用[J]. 系统仿真学报, 2025, 37(12): 3161-3175.
[10]	徐智霞, 王蕊, 孙楠, 何兵, 沈晓卫, 朱晓菲. 基于改进遗传算法的协同干扰资源分配问题研究[J]. 系统仿真学报, 2025, 37(12): 3176-3189.
[11]	刘翔, 金乾坤. 基于PAC-Bayes的多目标强化学习A2C算法研究[J]. 系统仿真学报, 2025, 37(12): 3212-3223.
[12]	杨兰英, 李超, 邹海锋, 万江涛, 张仁强, 刘惠, 卢宏. 基于改进蚁群算法与A*算法相融合的机器人路径规划优化[J]. 系统仿真学报, 2025, 37(11): 2956-2965.
[13]	苏筱婷, 张小威, 田义, 李奇, 王帅豪. 星光导航动态仿真场景时序设计方法研究[J]. 系统仿真学报, 2025, 37(11): 2946-2955.
[14]	张志利, 刘瑾, 周召发, 梁哲, 张云昊. 基于ISCSO-BP神经网络模型的光纤陀螺温度补偿技术研究[J]. 系统仿真学报, 2025, 37(11): 2904-2917.
[15]	陈际同, 周佳加, 吴迪, 江海龙. 基于TD3-RRT的特殊环境下USV路径规划算法研究[J]. 系统仿真学报, 2025, 37(11): 2888-2903.