Application of Facial Feature Localization Using Constrained Local Models in Template-Based Caricature Synthesis
Application of Facial Feature Localization Using Constrained Local Models in Template-Based Caricature Synthesis
复制标题
DOI：
10.1109/cisp.2009.5305490
复制
发表时间：
2009-10
期刊：
影响因子：
--
通讯作者：
Lei Wei;Rui Mo;Wei Gao;Yi Zhu;Z. Peng;Yaohui Zhang
中科院分区：
文献类型：
--
作者：
Lei Wei;Rui Mo;Wei Gao;Yi Zhu;Z. Peng;Yaohui Zhang
提出了一种准正面人脸漫画生成的三步法。首先，采用基于约束局部模型(CLM)和凸二次拟合(CQF)的人脸对齐方法获得人脸关键特征的初始位置。然后将面部成分(眉毛、眼睛、鼻子和嘴巴)分别按形态和外观定义为符合中国面貌的不同类别。使用决策树分类算法从预先分类的训练集中学习特征属性与对应类别之间的映射关系。最后，根据分类结果选择单独的人脸特征卡通模板，然后组装成具有表现力的漫画。实验结果表明，该方法在人脸漫画生成应用中具有较好的实用性和鲁棒性。
A three-step method for quasi-frontal face caricature generation is presented in the paper. First a CLM (constrained local models) and CQF (convex quadratic fitting) based face alignment approach is utilized to obtain initial locations of key facial features. Then facial components (eyebrow, eye, nose and mouth) are classified respectively into different categories defined by configuration and appearance in consistent with Chinese-Physiognomy. The mapping relationship between feature attributes and corresponding categories is learnt from a preclassified training set using the decision tree classification algorithm. Finally, separate facial feature cartoon templates are selected according to the classification results and then assembled to form an expressive caricature. Experimental results prove that the presented method is practical and robust for face caricature generation applications.