The Visual Computer

, Volume 12, Issue 5, pp 254–266 | Cite as

Constructing a 3D individualized head model from two orthogonal views

Original Articles

Abstract

A new scheme for constructing a 3D individualized head model automatically from only a side view and the front view of the face is presented. The approach instantiates a generic 3D head model based on a set of the individual's facial features extracted by a local maximum-curvature tracking (LMCT) algorithm that we have developed. A distortion vector field that deforms the generic model to that of the individual is computed by correspondence matching and interpolation. The input of the two facial images are blended and texture-mapped onto the 3D head model. Arbitrary views of a person can be generated from two orthogonal images and can be implemented efficiently on a low-cost, PC-based platform.

Key words

Image processing Computer graphics Facial images 3D headmodel 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aizawa K, Harashima H (1989) Model-based analysis synthesis image coding (MBASIC) system for a person's face. Signal Process Image Commun 1:139–152Google Scholar
  2. 2.
    Besl JR (1988) Active optical range imaging sensors. Machine Vis Appl 1:127–152Google Scholar
  3. 3.
    Chow G, Li XB (1993) Towards a system for automatic facial feature detection. Patt Recogn 26:1739–1755Google Scholar
  4. 4.
    Harmon LD, Kuo SC, Ramig PF, Raukivi U (1978) Identification of human face profiles by computer. Patt Recogn (10):301–312Google Scholar
  5. 5.
    Jiang Y-Z (1994) Acquiring 3-D models from sequences of contours. IEEE Trans Patt Anal Machine Intell 16:163–178Google Scholar
  6. 6.
    Kamel MS, Shen HC, Wong AKC, Campeanu RI (1993) System for the recognition of human faces. IBM Syst J 32:307–320Google Scholar
  7. 7.
    Kleiser J (1989) A fast, efficient, accurate way to represent the human face, SIGGRAPH'89, Course notes on state of the art in facial animation, pp 35–40Google Scholar
  8. 8.
    Magnenat-Thalmann N, Thalmann D (1987) The direction of synthetic actors in the film Rendez-vous à Montréal. IEEE Comp Graph Appl 7:9–12Google Scholar
  9. 9.
    Magnenat-Thalmann N, Thalmann D (1990) Synthetic actors in computer-generated 3D films. Springer, TokyoGoogle Scholar
  10. 10.
    Magnenat-Thalmann N, Minh HT, de Angelis M, Thalmann D (1989) Design, transformation and animation of human faces. Vis Comput 5:32–39Google Scholar
  11. 11.
    Paouri A, Magnenat-Thalmann N, Thalmann D (1991) Creating realistic three-dimensional human shape characters for computer-generated films. Proceedings of Computer Animation'91, Springer, Tokyo, pp 89–99Google Scholar
  12. 12.
    Rhodes ML (1991) Computer graphics in medicine: the past decade. IEEE Comp Graph Appl 11:52–54Google Scholar
  13. 13.
    Terzopoulos D, Waters K (1993) Analysis and synthesis of facial image sequences using physical and anatomical models. IEEE Trans Patt Anal Machine Intell 15:569–579Google Scholar
  14. 14.
    Vannier MW, Polgram T, Bhatia G, Brunsden B (1991) Facial surface scanner. IEEE Comp Graph Appl 11:72–80Google Scholar

Copyright information

© Springer-Verlag 1996

Authors and Affiliations

  1. 1.Image Computing Group, Department of Computer ScienceCity University of HongKongHong Kong

Personalised recommendations