Synthesizing Lateral Face From Frontal Facial Image Using Human Anthropometric Estimation

  • Authors:
  • J. C. Cheng;J. Moura

  • Affiliations:
  • -;-

  • Venue:
  • ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 1 - Volume 1
  • Year:
  • 1997

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we propose a method to synthesize a lateral face from a 20 gray-level image offrontal face that provides only plane geometry but not the depth in-formation for a 30 facial model. To estimate the depth information from the frontal face, we investigate the relationship between the frontal and lateral facial anthropometric parameters. According to anthropometric definitions on head and face, we setup a database consisting of facial parameters measured from 70 Chinese male adults. The database serves as prior knowl-edge for the minimum mean square error estimation on lateral facial parameters. For each person, with his frontal facial image, we can construct his 30 facial model based on the measured frontal facial parameters and the estimated lateral parameters. Therefore, image of lateral face can be synthesized by texture mapping from the frontal facial image.