Facial feature extraction from range images using a 3D morphable model Conference Paper uri icon

abstract

  • In this paper, a novel scheme is introduced for human facial feature extraction. Unlike previous methods that fit a 3D morphable model to 2D intensity images, our scheme utilizes 3D range images to extract features without requiring manually-defined initial landmark points. A linear transformation is used to achieve the mapping between the 3D model and a 3D range image, which makes the computation simple and fast. Moreover, our scheme is robust to the illumination and pose variations. In addition to features from range images, extra features can be obtained by examining optional 2D texture images. Using our scheme, we can also perform automatic eye/mouth corner localization. Experimental results show the high accuracy and robustness of our scheme. 2007 IEEE.

name of conference

  • 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07

published proceedings

  • 2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PTS 1-3

author list (cited authors)

  • Zou, L. e., Cheng, S., Xiong, Z., Lu, M. i., & Castleman, K.

citation count

  • 0

complete list of authors

  • Zou, Le||Cheng, Samuel||Xiong, Zixiang||Lu, Mi||Castleman, Kenneth

publication date

  • January 2007