Automatic generation of 3D faces expressing different utterances by modeling individual variation of shape deformation from expressionless faces

摘要

In this study, we used a Kinect V2 RGB-Depth sensor to measure the three-dimensional shape of faces and calculated theinformation of the differences among several individuals. Based on Principle Component Analysis of the obtainedinformation, we attempted to verify the possibility of generating various expressions from an inexpressive face of anarbitrary individual. Additionally, we attempted to improve the quality of generated utterance expressions.