基于MPEG-4的人脸表情图像变形研究.pdfVIP

基于MPEG-4 的人脸表情图像变形研究 戴振龙 朱海一 张申 贾珈 蔡莲红 (清华大学计算机系,北京,100084) 摘摘 要要 本文提出了一种基于MPEG-4 人脸动画框架的人脸表情图像变形方法，输入是一张中性人脸照片和一组人脸 摘摘 要要 动画参数 （FAP ），输出是对应的人脸表情图像。首先，采用Face Alignment 工具提取人脸照片中的88 个特征点；在此 基础上，对标准人脸网格进行校准变形，进一步生成特定人脸三角网格；然后根据FAP 参数移动相应的面部关键特征 点及其附近的关联特征点，移动过程中保证在多个FAP 参数的作用下人脸三角网格拓扑结构不变；最后对发生形变的 所有三角网格区域通过仿射变换进行面部纹理填充，生成由FAP 参数所定义的人脸表情图像。为了实现细微表情动作 和虚拟说话人合成，论文还实现了眼神表情动作和口内细节纹理的生成办法。基于MOS （5 分制）的主观评测实验表 明，利用本文提出的人脸图像变形方法生成的表情脸像自然度得分为 3.67 。虚拟说话人合成实验表明，该方法具有很 好的实时性，在普通PC 上的平均处理速度为15ms/帧，适用于实时视频处理和人脸动画生成。 关键词关键词 图像变形 人脸表情 MPEG-4 关键词关键词 MPEG-4 Based Facial Expression Image Morphing DAI Zhenlong, ZHU Haiyi, ZHANG Shen, JIA Jia, CAI Lianhong (Department of Computer Science, Tsinghua University, Beijing, 10084) Abstract Human face morphing is the foundation of facial expression synthesis and talking avatar animation. In this paper, an MPEG-4 based method for human face morphing and expression synthesis is proposed. The method uses a picture of neutral human face and a group of Face Animation Parameters (FAP) as input, and the output is corresponding facial expression image. There are four stages: facial feature point extraction, mesh generation for specific human face, mesh points movement driven by FAPs, and face texture mapping. After these four stages, photos of various facial expressions are created. Novel algorithms are also implemented for eyeball movement and texture mapping inside the mouth. Perceptual evaluation shows that the face morphing method can synthesize realistic and natural facial expressions for various human face models of different genders, ages and races. Meanwhile, this method is real-time, so it can be used in the areas of video processing and facial animation. Keywords Face morphing, Facial Expression, MPEG-4 变形进行参数化和标准化。 1 引