Please wait a minute...
浙江大学学报(工学版)
J4  2013, Vol. 47 Issue (6): 951-956    DOI: 10.3785/j.issn.1008-973X.2013.06.004
计算机技术     
保持纹理细节的无缝图像合成
吴金亮1，2, 黄海斌1, 刘利刚1，3
1. 浙江大学 数学系, 浙江 杭州 310027；2. 中国电子科技集团公司第54研究所，河北 石家庄 050081； 3. 中国科学技术大学 数学学院, 安徽 合肥 230026
Texture details preserving seamless image composition
WU Jin-liang1,2, HUANG Hai-bin1, LIU Li-gang1,3
1. Department of Mathematics, Zhejiang University, Hangzhou 310027, China； 2. The 54th Research of China Electronics Technology Group Corporation Shijiazhuang 050081, China； 3. School of Mathematical Sciences,University of Science and Technology of China, Hefei 230026, China
 全文: PDF 
摘要：

为了解决传统图像合成方法在处理具有不同纹理特征的图像时产生明显边界的问题, 提出新的图像合成框架.把图像分解为基本层和细节层，基本层解决边界处颜色的无缝融合|细节层实现边界处纹理细节的光滑过渡.算法流程为进行基本层的融合,合成新的细节层,新细节层添加到融合的基本层得到最终结果.通过计算一张权重图来指导新细节层的生成,权重图度量纹理特征的强弱和像素到边界的距离.实验结果显示:算法可以有效保证颜色的无缝融合,保持纹理的光滑过渡.相对于传统图像合成方法,该算法可以生成更真实的合成图像.
关键词： 图像合成;  泊松图像编辑;  图像分解;  抠像;  图像融合    
Abstract:

In order to resolve the apparent boundary issue that the conventional image compositing method encounters when applied to images of different texture details,  a new image compositing framework was proposed, which decomposed an image to a base layer and a detail layer, the base layer implementing the seamless fusion of color at the boundary, while the detail layer implementing the smooth transition of texture details at the boundary. The processing was as follows: fusing the base layer,  synthesizing a new detail layer and then adding it to the fused base layer to get the final result. A weight map was computed by the measure of texture details and distances of pixels to the boundary and used to guide the generation of new detail layer. Experimental results on many images of different texture features showed that the proposed algorithm can effectively realize the seamless fusion of color and smooth transition of texture details. The proposed method produced more realistic composites than the traditional method.
Key words: image composition    Poisson image editing    image decomposition    matting    image fusion
出版日期: 2013-07-09
:  TP 391  
基金资助:

国家自然科学优秀青年基金资助项目61222206)；国家自然科学基金资助项目61070071)；国家“973”重点基础研究发展规划基金资助项目2011CB302400).
通讯作者: 刘利刚，男，教授.     E-mail: lgliu@ustc.edu.cn
作者简介: 吴金亮（1984—），男，博士生，从事数字图像处理和计算机图形学研究. E-mail: jinliangwu@zju.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

吴金亮, 黄海斌, 刘利刚. 保持纹理细节的无缝图像合成[J]. J4, 2013, 47(6): 951-956.

WU Jin-liang, HUANG Hai-bin, LIU Li-gang. Texture details preserving seamless image composition. J4, 2013, 47(6): 951-956.

链接本文:

http://www.zjujournals.com/xueshu/eng/CN/10.3785/j.issn.1008-973X.2013.06.004    或    http://www.zjujournals.com/xueshu/eng/CN/Y2013/V47/I6/951

［1］ PREZ P, GANGNET M, BLAKE A. Poisson image editing［J］. ACM Transactions on Graphics, 2003, 22(3): 313-318.

［2］ BURT P J, ADELSON E H. A multiresolution spline with application to image mosaics［J］. ACM Transactions on Graphics, 1983, 2(4): 217-236.

［3］ AGARWALA A, DONTCHEVA M, AGRAWALA M, et al. Interactive digital photomontage［J］. ACM Transactions on Graphics, 2004, 23(3): 294-302.

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

［5］ BURT P J, ADELSON E H. The laplacian pyramid as a compact image code［J］. IEEE Transactions on Communications, 1983, 31(4): 532-540.

［6］ JOBSON D, RAHMAN Z, WOODELL G. A multi-scale retinex for bridging the gap between color images and the human observation of scenes［J］. IEEE Transactions on Image Processing, Special Issue on Color Processing, 1997, 6(7): 965-976.

［7］ PATTANAIK S N, FAIRCHILD M, FERWERDA J, et al. Multiscale model of adaptation, spatial vision and color appearance［C］∥Proceeding of the Sixth Color Imaging Conference, Society for Imaging Science and Technology.Scottsdale, USA:［s.n.］,1998: 27.

［8］ TOMASI C, MANDUCHI R. Bilateral filtering for gray and color images［C］∥Proceeding of the Sixth International Conference on Computer Vision. Bombay, India: IEEE Computer Society, 1998: 836-846.

［9］ DURAND F, DORSEY J. Fast bilateral filtering for the display of high-dynamic-range images［J］. ACM Transactions on Graphics, 2002, 21(3): 257-266.

［10］ CHOUDHURY P, TUMBLIN J. The trilateral filter for high contrast images and meshes［C］∥In SIGGRAPH 05: ACM SIGGRAPH 2005 Courses. New York, USA: ACM, 2005.

［11］ BAE S, PARIS S., DURAND F. Two-scale tone management for photographic look［J］. ACM Transactions on Graphics, 2006, 25(3) : 637-645.

［12］ SUBR K, SOLER C, DURAND F. Edge-preserving Multiscale Image Decompostion based on Local Extrema［J］. ACM Transactions on Graphics, 2009, 28(5): 147-155.

［13］ RUZON M, TOMASI C. Alpha estimation in natural images［C］ ∥Proceeding of IEEE CVPR’00. Hilton Head, SC, USA: IEEE Computer Society, 2000: 18-25.

［14］ CHUANG Y Y, CURLESS B, SALESIN D H, et al. A bayesian approach to digital matting［C］ ∥Proceeding of IEEE CVPR’01. Kauai, HI, USA: IEEE Computer Society, 2001: 264-271.

［15］ SUN J, JIA J, TANG C K, et al. Poisson matting［J］. ACM Transactions on Graphics, 2004, 23(3): 315-321.

［16］ LEVIN A, LISCHINSKI D, WEISS Y. A Closed Form Solution to Natural Image Matting［J］. IEEE Transactions on Pattern Analysis and Machine Intelligenc, 2008, 30(2): 228-242.

［17］ TAO M, JOHNSON M, AND PARIS S. Error-Tolerant Image Compositing［C］ ∥Proc of ECCV′10. Heraklion, Crete, Greece: Springer, 2010: 31-44.
[1] 陈阔, 冯华君, 徐之海, 李奇, 陈跃庭. 细节保持的快速曝光融合[J]. 浙江大学学报(工学版), 2015, 49(6): 1048-1054.
[2] 江燊煜,陈阔,徐之海,冯华君,李奇,陈跃庭. 基于曝光适度评价的多曝光图像融合方法[J]. 浙江大学学报(工学版), 2015, 49(3): 470-475.
[3] 周强, 赵巨峰, 冯华君, 徐之海, 李奇, 陈跃庭. 非下采样剪切波的红外偏振图像融合[J]. 浙江大学学报(工学版), 2014, 48(8): 1508-1516.
[4] 胡根生,鲍文霞,梁栋,张为. 基于SVR和贝叶斯方法的全色与多光谱图像融合[J]. J4, 2013, 47(7): 1258-1266.
[5] 彭海,赵巨峰,冯华君,徐之海,李奇,陈跃庭. 基于区域显著性的双波段图像融合方法[J]. J4, 2012, 46(11): 2109-2115.
[6] 焦竹青, 邵金涛, 徐保国. 非下采样Contourlet变换域多聚焦图像融合方法[J]. J4, 2010, 44(7): 1333-1337.
[7] 崔扬 蔡晋辉 周泽魁. 基于小波变换的纹理图像融合[J]. J4, 2005, 39(9): 1339-1342.
[8] 章东平 祝金标 刘济林. 自动定位彩色图像中的文本[J]. J4, 2005, 39(2): 229-233.