image2
image3
image4
image5
image6
image7
image1

Real-Time Facial Feature Tracking and Speech Acquisition for Cloned Head

Goto, T. and Kshirsagar, S. and Magnenat-Thalmann, N.


Abstract: In this paper, we describe the components of the system used for real time facial communication using cloned head. We begin with describing the automatic face cloning using two orthogonal photographs of a person. The steps in this process are the face model matching and texture generation. After a brief introduction to the MPEG4 parameters that we are using, we proceed with the explanation of the facial feature tracking using a video camera. The technique requires an initialization step and is further divided into mouth and eye tracking. These steps are explained in detail. We then explain the speech processing techniques used for real time phoneme extraction and subsequent speech animation module. We conclude with the results and comments on the integration of the modules towards a complete system.


@article{3,
  journal = {IEEE Signal Processing Magazine},
  author = {Goto, T. and Kshirsagar, S. and Magnenat-Thalmann, N.},
  title = {Real-Time Facial Feature Tracking and Speech Acquisition for Cloned Head},
  publisher = {IEEE Publisher},
  volume = {Vol. 18},
  number = {No. 3},
  pages = {17-25},
  month = may,
  year = {2001},
  topic = {Facial Animation}
}