Please wait a minute...
浙江大学学报(工学版)
自动化技术、通信工程     
改进线性模板映射的色彩转移算法
方力洋, 王进, 陆国栋
浙江大学 CAD&CG国家重点实验室,浙江 杭州 310027
Color transfer algorithm based on improved linear template mapping
FANG Li yang, WANG Jin, LU Guo dong
State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou 310027, China
 全文: PDF(3099 KB)   HTML
摘要:

针对线性模板映射方法只适用于模板和较单一色彩图像之间的转移的缺点,提出一种改进的色彩转移算法.采用Grabcut进行区域分割,由区域面积比例、亮度统计信息、色彩分布信息组成匹配向量,确定区域之间的匹配对应关系|针对色彩区域较小时因色彩分布集中而影响色彩转移准确性的问题,利用色彩分布进行修正,并采用最近点搜索方法完成各区域的色彩转移|最后利用直方图规定化对亮度进行修正. 实验结果表明:改进的算法在局部细节和整体的色彩转移上都能取得较好的效果.

Abstract:

An improved color transfer algorithm was proposed to overcome the limit of the color transfer algorithm based on linear template mapping that just worked well on templates and between dull color images. First, grab cut was introduced for image segmentation, and a region match method based on match vectors was proposed, consisting of region ration, luminance statistical information and color distribution of each regions. Secondly, the correction of color distribution was applied to improve the accuracy of color transfer between small regions, then the nearest point searching method was taken to achieve regional color transfer. Finally, a luminance correction was proposed based on histogram specification to overcome the defect in original algorithm without luminance change. The experimental results show that better details and global color transferring results can be achieved by the proposed algorithm.

出版日期: 2016-06-01
:  TP 391  
基金资助:

 国家自然科学基金资助项目(51275460),浙江省公益技术研究工业资助项目(2013C31046),高等学校博士学科点专项基金资助项目(20110101120005).

通讯作者: 王进,男,副教授.ORCID:000000033106021X.     E-mail: dwjcom@zju.edu.cn
作者简介: 方力洋(1989—),男,博士生,从事CAD/CG研究. ORCID:0000000228371255. E-mail: fly305802@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:

方力洋, 王进, 陆国栋. 改进线性模板映射的色彩转移算法[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008973X.2016.06.013.

FANG Li yang, WANG Jin, LU Guo dong. Color transfer algorithm based on improved linear template mapping. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008973X.2016.06.013.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008973X.2016.06.013        http://www.zjujournals.com/eng/CN/Y2016/V50/I6/1103

[1] REINHARD E, ASHIKHMIN M, BRUCE G, et a1. Color transfer between images [J]. IEEE Computer Graphics and Applications, 2001, 21(5): 34-41.
[2] XIAO X Z, MA L Z. Gradientpreserving color transfer [J]. Computer Graphics Forum, 2009, 28(7): 1879-1886.
[3] LIU S G, SUN H Q, ZHANG X. Selective color transferring via ellipsoid color mixture map [J]. Journal of Visual Communication and Image Representation, 2012, 23(1): 173-181.
[4] HUANG Y H, WANG P C, CHOU C C, et al. An automatic selective color transfer algorithm for images [C]∥ Proceedings of the 2011 ACM Symposium on Applied Computing. TaiChung: ACM, 2011: 66 -71.
[5] SEO S H, PARK Y S, OSTROMOUKHOV V. Image recoloring using linear template mapping [J]. Multimedia Tools and Applications, 2013, 64(2): 293-308.
[6] YOUNGBAE H, JOON Y L, IN S K, et a1. Color transfer using probabilistic moving least squares [C]∥ 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus: IEEE, 2014:3342-3349.
[7] FUMIO O, KENNETH V, ADRIENB, et al. Unifying color and texture transfer for predictive appearance manipulation [J]. Computer Graphics Forum, 2015, 34 (4): 11-21.
[8] PAPADAKIS N, PROVENZI E, CASELLES V. A variational model for histogram transfer of color images [J]. IEEE Transactions on image processing, 2011,20(6): 16821695.
[9] XIAO Y, WAN L, LEUNG C S, et al.Optimization based gradient mesh color transfer [J]. Computer Graphics Forum, 2015, 34(6):123-134.
[10] ZHANG W, CAO C, CHEN S F, et al. Style transfer via image component analysis [J]. IEEE Transactions on multimedia, 2013,15(7): 15941601.
[11] TAI Y W, JIA J Y, TANG C K. Local color transfer via probabilistic segmentation by expectation maximization [C]∥ In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005(1): 747-754.
[12] CUSANO C, GASPARINI F, SCHENTTINI R. Color transfer using semantic image annotation [C]∥ International Society for Optics and Photonics. Burlingame:[s. n.], 2012: 82990U82990U8.
[13] ZENG K, ZHANG R M, LAN X D, et al. Color style transfer by constraint locally linear embedding [C]∥ 18th International Conference on Image Processing (ICIP). Brussels: IEEE, 2011: 1121-1124.
[14] XIAO H, WANG J J, LIAN H C. Affective image adjustment with a single word [J]. The Visual Computer: International Journal of Computer Graphics, 2013, 29(11): 1121-1133.
[15] ROTHER C, KOLMOGOROV V, BLAKE A. Grabcut: Interactive foreground extraction using iterated graph cuts [J]. ACM Transactions on Graphics (TOG), 2004, 23(3): 309-314. [16] 钱小燕,肖亮,吴慧中.模糊颜色聚类在颜色传输中的应用[J].计算机辅助设计与图形学学报,2006,18(9): 1332-1336.
QIAN Xiaoyan, XIAO Liang, WU Huizhong. Application of fuzzy color cluster in color transfer between Images [J]. Journal of computeraided design and computer graphics, 2006,18(9): 1332-1336.

[1] 何雪军, 王进, 陆国栋, 刘振宇, 陈立, 金晶. 基于三角网切片及碰撞检测的工业机器人三维头像雕刻[J]. 浙江大学学报(工学版), 2017, 51(6): 1104-1110.
[2] 王桦, 韩同阳, 周可. 公安情报中基于关键图谱的群体发现算法[J]. 浙江大学学报(工学版), 2017, 51(6): 1173-1180.
[3] 尤海辉, 马增益, 唐义军, 王月兰, 郑林, 俞钟, 吉澄军. 循环流化床入炉垃圾热值软测量[J]. 浙江大学学报(工学版), 2017, 51(6): 1163-1172.
[4] 毕晓君, 王佳荟. 基于混合学习策略的教与学优化算法[J]. 浙江大学学报(工学版), 2017, 51(5): 1024-1031.
[5] 穆晶晶, 赵昕玥, 何再兴, 张树有. 基于凹凸变换与圆周拟合的重叠气泡轮廓重构[J]. 浙江大学学报(工学版), 2017, 51(4): 714-721.
[6] 黄正宇, 蒋鑫龙, 刘军发, 陈益强, 谷洋. 基于融合特征的半监督流形约束定位方法[J]. 浙江大学学报(工学版), 2017, 51(4): 655-662.
[7] 蒋鑫龙, 陈益强, 刘军发, 忽丽莎, 沈建飞. 面向自闭症患者社交距离认知的可穿戴系统[J]. 浙江大学学报(工学版), 2017, 51(4): 637-647.
[8] 王亮, 於志文, 郭斌. 基于双层多粒度知识发现的移动轨迹预测模型[J]. 浙江大学学报(工学版), 2017, 51(4): 669-674.
[9] 廖苗, 赵于前, 曾业战, 黄忠朝, 张丙奎, 邹北骥. 基于支持向量机和椭圆拟合的细胞图像自动分割[J]. 浙江大学学报(工学版), 2017, 51(4): 722-728.
[10] 戴彩艳, 陈崚, 李斌, 陈伯伦. 复杂网络中的抽样链接预测[J]. 浙江大学学报(工学版), 2017, 51(3): 554-561.
[11] 刘磊, 杨鹏, 刘作军. 采用多核相关向量机的人体步态识别[J]. 浙江大学学报(工学版), 2017, 51(3): 562-571.
[12] 郭梦丽, 达飞鹏, 邓星, 盖绍彦. 基于关键点和局部特征的三维人脸识别[J]. 浙江大学学报(工学版), 2017, 51(3): 584-589.
[13] 王海军, 葛红娟, 张圣燕. 基于核协同表示的快速目标跟踪算法[J]. 浙江大学学报(工学版), 2017, 51(2): 399-407.
[14] 张亚楠, 陈德运, 王莹洁, 刘宇鹏. 基于增量图形模式匹配的动态冷启动推荐方法[J]. 浙江大学学报(工学版), 2017, 51(2): 408-415.
[15] 刘宇鹏, 乔秀明, 赵石磊, 马春光. 统计机器翻译中大规模特征的深度融合[J]. 浙江大学学报(工学版), 2017, 51(1): 46-56.