Detection of Computer Generated Faces in Videos Based on Pulse Signal

摘要

The rapid development in the field of computer graphics (CG) makes it quite easy to create photo-realistic images and videos. This brings forward an emergent requirement for techniques that can distinguish CG from real contents. In this paper, we propose a method that leverages human pulse signal to distinguish between CG and real videos that include human faces. We use a robust tracking method to locate a patch of skin on the face. Then, a chrominance-based algorithm is employed to robustly extract pulse signal. By checking the frequency waveform of the extracted pulse signal, we can tell CG and real videos apart. The experiment shows encouraging results, which demonstrate the efficiency of our method.

出版物
IEEE China Summit and International Conference on Signal and Information Processing
彭勃
彭勃
副研究员
王伟
王伟
副研究员、硕导

主要从事多媒体内容安全、人工智能安全、多模态内容分析与理解等方面的研究工作。

董晶
董晶
研究员、硕导

主要从事多媒体内容安全、人工智能安全、多模态内容分析与理解等方面的研究工作。详情访问:http://cripac.ia.ac.cn/people/jdong

谭铁牛
谭铁牛
研究员,博导

主要从事图像处理、计算机视觉和模式识别等相关领域的研究工作,目前的研究主要集中在生物特征识别、图像视频理解和信息内容安全等三个方向。