结合人脸表情和变形技术的人脸卡通动画系统设计与实现Design and implementation of human face cartoon animation system combining face expressions and deformation technology
伍菲
摘要(Abstract)：
针对实时生成人脸卡通动画的需求,设计和实现一种结合人脸表情与变形技术的人脸卡通动画系统。该系统包括人脸检测、特征点定位、人脸表情生成和人脸变形4个部分,首先,使用Haar特征和级联AdaBoost分类器检测人脸,并使用主动形状模型定位人脸特征点;然后,根据人脸特征和已有的卡通素材器官合成与真实人脸所对应的卡通人脸,并合成动态表情;最后,使用图像变形技术对人脸进行夸张变形处理,生成具有幽默、夸张效果的人脸图像。基于Matlab的实现效果表明,该系统能实时、高效地处理真实人脸图像。
关键词(KeyWords)： 卡通人脸;图像处理;人脸表情;图像变形;人脸检测;AdaBoost
基金项目(Foundation): 2017年度广西高校中青年教师基础能力提升项目(2017KY1341)~~
作者(Author): 伍菲
DOI: 10.16652/j.issn.1004-373x.2018.12.014
参考文献(References)：
- [1]李君涵.针对视频的人脸卡通化方法研究[D].成都:电子科技大学,2016.LI Junhan.Research on video based face cartoon method[D].Chengdu:University of Electronic Science and Technology of China,2016.
- [2]宋阳,刘艳丽.基于照片的可编辑光照效果卡通人脸生成算法[J].图学学报,2015,36(1):83-89.SONG Yang,LIU Yanli.An algorithm generating human face cartoon portrait including light editing based on photo[J].Journal of graphics,2015,36(1):83-89.
- [3]刘胜.基于Gabor小波的人脸表情识别研究[D].武汉:华中科技大学,2015.LIU Sheng.Studies on facial expression recognition based on Gabor wavelet[D].Wuhan:Huazhong University of Science and Technology,2015.
- [4]郭耸,顾国昌,蔡则苏,等.基于特征融合与决策树级联结构的多姿态人脸检测[J].沈阳工业大学学报,2012,34(2):203-208.GUO Song,GU Guochang,CAI Zesu,et al.Multi-pose face detection based on feature fusion and decision tree cascade structure[J].Journal of Shenyang University of Technology,2012,34(2):203-208.
- [5]王寅.基于局部自适应核回归的Ada Boost人脸检测算法研究[D].南京:南京航空航天大学,2012.WANG Yin.Research on Ada Boost face detection algorithm based on local adaptive kernel regression[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2012.
- [6]ZHOU J,TONG X,LIU Z,et al.3D cartoon face generation by local deformation mapping[J].Visual computer,2016,32(6-8):717-727.
- [7]李帅.风格化人脸肖像漫画生成技术的研究与实现[D].桂林:桂林电子科技大学,2015.LI Shuai.Research and implementation of stylized face portrait cartoons generation technology[D].Guilin:Guilin University of Electronic Technology,2015.
- [8]范玉磊.基于Ada Boost与SVM的人脸表情识别研究[D].太原:中北大学,2011.FAN Yulei.Face expression recognition based on Ada Boost and SVM[D].Taiyuan:North University of China,2011.
- [9]牛连强,赵子天,张胜男.基于Gabor特征融合与LBP直方图的人脸表情特征提取方法[J].沈阳工业大学学报,2016,38(1):63-68.NIU Lianqiang,ZHAO Zitian,ZHANG Shengnan.Extraction method for facial expression features based on Gabor feature fusion and LBP histogram[J].Journal of Shenyang University of Technology,2016,38(1):63-68.
- [10]高娜,彭亚丽,高佳美,等.结合主成分分析和局部导数模式的人脸识别方法[J].现代电子技术,2014,37(18):1-5.GAO Na,PENG Yali,GAO Jiamei,et al.Face recognition method combining principal component analysis with local derivative pattern[J].Modern electronics technique,2014,37(18):1-5.
- [11]KNUTSEN D,ROS C,BIGOT L L.Generating references in naturalistic face-to-face and phone-mediated dialog settings[J].Topics in cognitive science,2016,8(4):796-818.
- [12]GILANI S Z,MIAN A,EASTWOOD P.Deep,dense and accurate 3D face correspondence for generating population specific deformable models[J].Pattern recognition,2017,69:238-250.
- [13]DU Y,WANG Y.Generating virtual training samples for sparse representation of face images and face recognition[J].Journal of modern optics,2016,63(6):1-9.