Automatic Generation of Facial Expression Using Generative Adversarial Nets
Automatic Generation of Facial Expression Using Generative Adversarial Nets
复制标题
DOI：
10.1109/gcce.2018.8574866
复制
发表时间：
2018-10
期刊：
影响因子：
--
通讯作者：
Yoshiharu Kawai;M. Seo;Yenwei Chen
中科院分区：
文献类型：
--
作者：
Yoshiharu Kawai;M. Seo;Yenwei Chen
随着数码相机、智能手机和SNS的普及，人们的面部图像数量增加。从单个面部图像生成面部表情已经广泛应用于娱乐和社交领域。已经开发了许多应用机器学习技术的方法。在我们之前的研究中，我们开发了一个化妆模拟器系统。然而，该系统不能基于面部表情的变化来改变化妆面部的印象;此外，另一个挑战是用户不能动态地和客观地看到化妆的印象。因此，在这项研究中，我们从一个自然的（无表情）图像生成静态面部表情图像通过使用生成对抗网络，这是关键的动态面部表情变化的研究。我们的实验结果表明，我们的方法实现了最好的表情图像。
With the spread of digital cameras, smart phones, and SNS, the number facial images of people have increased. Facial expression generation from a single facial image has been widely applied to the fields of entertainment and social communication. Many approaches that apply machine learning techniques have been developed. In our previous study, we developed a makeup simulator system. However, this system is incapable of changing the impression of a cosmetic face based on changes in facial expression; in addition, another challenge is that the user cannot see the impression of makeup dynamically and objectively. Therefore, in this study, we generate static facial expression images from a natural (expressionless) image by using generative adversarial networks, which is critical to the research on dynamic facial expression change. Our experimental results demonstrate that our approach achieves the best expression image.