首页 > 论文 > 液晶与显示 > 33卷 > 2期(pp:156-164)

基于采样抠图和自适应颜色的图像合成算法

Image synthesis algorithm based on sample cutout and adaptive color

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对图像合成结果易受颜色取样和权值选取影响等问题, 本文借鉴梯度域和线性alpha合成算法的优点, 提出了一种基于采样抠图和自适应颜色权值的图像合成算法。算法首先通过增加数据项约束和邻域限制对原始抠图方法得到的alpha matte值进行局部迭代修正, 根据得到的alpha matte值对合成区域进行划分, 不同的合成区域采用不同的合成策略, 边缘区域采用梯度域合成方法对边界进行无缝对接和颜色保真, 同时利用均值插值重建方程求解, 降低求解复杂度;内部区域通过亮度对比系数计算自适应颜色权值, 并用其进行内部区域颜色再平衡, 保证源图像和目标图像的完美融合。仿真实验表明, 该算法与其他合成算法相比, 在无缝边界的同时, 颜色保证处理更为有效。

Abstract

As for the problem that image synthesis result is subject to color and weight selection, the paper proposes an image synthesis algorithm based on sampling cutout and adaptive color weight by combining the advantages of gradient domain and linear alpha synthesis algorithm. This algorithm increases data item constraints and neighborhood restrictions to realize the local iteration correction of alpha matte value obtained through the original cutout method. The synthesis area is divided according to the obtained alpha matte value. Different synthesis strategies are adopted for different synthesis areas. Gradient domain synthesis method is used for seamless docking and color fidelity of borders. Besides, an equation is re-created with mean interpolation and then the solution is obtained. Thereby, the solving process is simplified. For the internal area, the adaptive color weight is calculated with the use of brightness contrast factor. Besides, the colors of the internal area are further balanced so as to ensure the perfect integration of source image and target image. The simulation experiment shows that the algorithm achieves more effective color maintenance while creating the seamless border than other synthesis algorithms.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/yjyxs20183302.0156

所属栏目:图像处理

收稿日期:2017-06-04

修改稿日期:2017-10-30

网络出版日期:--

作者单位    点击查看

李 娜:黄河交通学院 机电工程学院,河南 焦作 454950
王 丹:黄河交通学院 机电工程学院,河南 焦作 454950

联系人作者:李娜(lina198003@126.com)

备注:李娜(1980-),女, 河南开封人, 硕士, 讲师, 研究方向:数据挖掘与图形图像处理。

【1】AFIFI M, HUSSAIN K F. MPB: A modified Poisson blending technique [J]. Computational Visual Media, 2015, 1(4): 331-341.

【2】JIA J Y, SUN J, TANG C K, et al. Drag-and-drop pasting [J]. ACM Transactions on Graphics (TOG), 2006, 25(3): 631-637.

【3】DARABI S, SHECHTMAN E, BARNES C, et al. Image melding: combining inconsistent images using patch-based synthesis [J]. ACM Transactions on Graphics (TOG), 2012, 31(4): 82.

【4】DU H, JIN X G. Object cloning using constrained mean value interpolation [J]. The Visual Computer, 2013, 29(3): 217-229.

【5】BIE X H, WANG, W C, SUN H Q, et al. Intent-aware image cloning [J]. The Visual Computer, 2013, 29(6/8): 599-608.

【6】CHEN T, ZHU J Y, SHAMIR A, et al. Motion-aware gradient domain video composition [J]. IEEE Transactions on Image Processing, 2013, 22(7): 2532-2544.

【7】YANG W X, ZHENG J M, CAI J F, et al. Natural and seamless image composition with color control [J]. IEEE Transactions on Image Processing, 2009, 18(11): 2584-2592.

【8】HENZ B, LIMBERGER F A, OLIVEIRA M M. Color adjustment for seamless cloning based on Laplacian-membrane modulation [C]//Proceedings of the 28th SIBGRAPI Conference on Graphics, Patterns and Images. Salvador, Brazil: IEEE, 2015: 196-202.

【9】李贝, 汪浩, 于佳骏, 等.颜色协调的鲁棒式图像克隆[J].系统仿真学报, 2015, 27(4):723-730.
LI B,WANG H, YU J J, et al. Robust image cloning with color harmonization [J]. Journal of System Simulation, 2015, 27(4): 723-730. (in Chinese)

【10】WANG D, JIA W J, LI G Q, et al. Natural image composition with inhomogeneous boundaries [C]//Proceedings of the 5th Pacific Rim Symposium on Image and Video Technology. Gwangju, South Korea: Springer, 2011: 92-103.

【11】BIE X H, HUANG H D, WANG W C. Free appearance-editing with improved Poisson image cloning [J]. Journal of Computer Science and Technology, 2011, 26(6): 1011-1016.

【12】WU H, XU D. Color preserved image compositing[C]//Proceedings of the 3rd International Conference on Multimedia Technology (ICMT 2013). Berlin Heidelberg: Springer, 2014: 325-333.

【13】LEVIN A, LISCHINSKI D, WEISS Y. A closed-form solution to natural image matting [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(2): 228-242.

【14】GRADY L. Random walks for image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(11): 1768-1783.

【15】RHEMANN C, ROTHER C, WANG J, et al. A perceptually motivated online benchmark for image matting [C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA: IEEE, 2009: 1826-1833.

【16】WANG J, COHEN M F. Optimized color sampling for robust matting [C]//Proceedings of 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN, USA: IEEE, 2007: 1-8.

【17】ROTHER C, KOLMOGOROV V, BLAKE A. "GrabCut": interactive foreground extraction using iterated graph cuts [C]//Proceedings of the ACM SIGGRAPH 2004 Papers. Los Angeles, California: ACM, 2004: 309-314.

【18】CHEN Q F, LI D Z Y, TANG C K. KNN matting [C]//Proceedings of 2012 Conference on Computer Vision and Pattern Recognition. Providence, RI, USA: IEEE, 2012: 869-876.

【19】SHAHRIAN E, RAJAN D, PRICE B, et al. Improving image matting using comprehensive sampling sets [C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, OR, USA: IEEE, 2013: 636-643.

【20】PREZ P, GANGNET M, BLAKE A. Poisson image editing [J]. ACM Transactions on Graphics (TOG), 2003, 22(3): 313-318.

【21】DING Y D, WEI X C, PANG H B, et al. Fusion of object and scene based on IHS transform and SFIM [C]//Proceedings of the 6th International Conference on Image and Graphics. Hefei, Anhui, China: IEEE, 2011: 702-706.

引用该论文

LI Na,WANG Dan. Image synthesis algorithm based on sample cutout and adaptive color[J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33(2): 156-164

李 娜,王 丹. 基于采样抠图和自适应颜色的图像合成算法[J]. 液晶与显示, 2018, 33(2): 156-164

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF