利用双边滤波器和DoG算子的人像卡通化新算法
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:A New Approach for Cartoon-Like Stylization of Video Portrait Based on Bilateral Filter and DoG Operator
  • 作者:曾冬梅 ; 陈锻生
  • 英文作者:ZENG Dong-mei;CHEN Duan-sheng;College of Computer Science and Technology,Huaqiao University;
  • 关键词:双边滤波器 ; 高斯差分算子 ; 图像卡通化 ; 软量化
  • 英文关键词:bilateral filter;;difference of Gaussians operator;;image cartoon-like stylization;;soft quantization
  • 中文刊名:HQDB
  • 英文刊名:Journal of Huaqiao University(Natural Science)
  • 机构:华侨大学计算机科学与技术学院;
  • 出版日期:2013-06-19 15:19
  • 出版单位:华侨大学学报(自然科学版)
  • 年:2014
  • 期:v.35;No.136
  • 基金:福建省科技计划重点项目(2011H0028);福建省科技计划重大项目(2011H6016)
  • 语种:中文;
  • 页:HQDB201402008
  • 页数:5
  • CN:02
  • ISSN:35-1079/N
  • 分类号:42-46
摘要
利用双边滤波器在平滑图像的同时又能保持边缘的良好特性,结合DoG(高斯差分)算子,提出人像卡通化的新算法.该算法首先应用双边滤波器对原始的彩色图像进行平滑,在获得颜色主要特征的同时,去除一些不重要的细节信息,简化了低对比度区域;然后,融入用DoG算子检测到的边缘曲线来增强高对比度区域;最后进行软量化以获得卡通图像.实验结果表明:相对经典的图像抽象化方法而言,该算法获得了更好的图像卡通化效果和更快的速度.
        Using the good characteristic that bilateral filter can also preserve edges while smoothing image,combining with DoG(difference of Gaussians)operator,this paper proposes a new approach for cartoon-like stylization of video portrait.First,the approach applied bilateral filter to smooth the original color image.While getting the dominant features of color,it could removal some trivial details and simplify the low contrast regions.Then,the edge curves detected by DoG operator were integrated to enhance the high contrast regions.At last,the soft quantization was applied to stylize portrait.The experimental results show the approach achieves better effect of image cartoon-like stylization and faster speed relative to classic method of image abstraction.
引文
[1]周科颖.图像风格化技术研究及平台开发[D].浙江:浙江工业大学,2010:2-3.
    [2]郭纳.图像的卡通风格渲染技术[D].山东:青岛大学,2009:4.
    [3]樊雅平,黄生学.基于Mean-shift和DoG的卡通化图像生成算法[J].煤炭技术,2009,28(9):160-161.
    [4]DECARKI D,SANTELLA A.Stylization and abstraction of photographs[J].ACM Transactions on Graphics,2002,21(3):769-776.
    [5]SANTELLA A,DECARLO D.Visual interest and NPR:An evaluation and manifesto[C]∥Proceedings of the 2004NPAR.New York:ACM Press,2004:71-78.
    [6]WANG Jue,XU Ying-qing,SHUM H Y,et al.Video tooning[J].ACM Transactions on Graphics,2004,23(3):574-583.
    [7]COLLOMOSSE J P,ROWBTREE D,HALL P M.Stroke surfaces:Temporally coherent artistic animations from video[J].IEEE Transactions on Visualization and Computer Graphics,2005,11(5):540-549.
    [8]GOOCH B,REINHARD E,GOOCH A.Human facial illustrations:Creation and psychophysical evaluation[J].ACM Transactions on Graphics,2004,23(1):27-44.
    [9]WINNEMOLLER H,OLSEN S C,GOOCH B.Real-time video abstraction[J].ACM Transactions on Graphics,2006,25(3):1221-1226.
    [10]TOMASI C,MANDUCHI R.Bilateral filtering for gray and color images[C]∥Proceedings of the 1998IEEE International Conference on Computer Vision.Bombay:IEEE Press,1998:839-846.
    [11]MARR D,HILDRETH E C.Theory of edge detection[C]∥Proceedings of the Royal Society of London Biological Sciences.London:Defense Technical Information Center,1980:187-217.
    [12]WINNEMOLLER H,KYPRIANIDIS J E,OLSEN S.XDoG:An extended difference-of-Gaussians compendium including advanced image stylization[J].Computers&Graphics,2012,36(6):740-753.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700