3D Facial Modelling for Model-Based Coding
Summary :
We describe an approach for modelling a person's face for model-based coding. The goal is to estimate the 3D shape by combining the contour analysis and shading analysis of the human face image in order to increase the quality of the estimated 3D shape. The motivation for combining contour and shading cues comes from the observation that the shading cue leads to severe errors near the occluding boundary, while the occluding contour cue provides incomplete surface information in regions away from contours. Towards this, we use the deformable model as the common level of integration such that a higher-quality measurement will dominate the depth estimate. The feasibility of our approach is demonstrated using a real facial image.
- Publication
- IEICE TRANSACTIONS on Communications Vol.E76-B No.6 pp.626-633
- Publication Date
- 1993/06/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Issue on Next Generation Visual Telecommunication and Broadcasting)
- Category
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Hiroyuki MORIKAWA, Eiji KONDO, Hiroshi HARASHIMA, "3D Facial Modelling for Model-Based Coding" in IEICE TRANSACTIONS on Communications,
vol. E76-B, no. 6, pp. 626-633, June 1993, doi: .
Abstract: We describe an approach for modelling a person's face for model-based coding. The goal is to estimate the 3D shape by combining the contour analysis and shading analysis of the human face image in order to increase the quality of the estimated 3D shape. The motivation for combining contour and shading cues comes from the observation that the shading cue leads to severe errors near the occluding boundary, while the occluding contour cue provides incomplete surface information in regions away from contours. Towards this, we use the deformable model as the common level of integration such that a higher-quality measurement will dominate the depth estimate. The feasibility of our approach is demonstrated using a real facial image.
URL: https://global.ieice.org/en_transactions/communications/10.1587/e76-b_6_626/_p
Copy
@ARTICLE{e76-b_6_626,
author={Hiroyuki MORIKAWA, Eiji KONDO, Hiroshi HARASHIMA, },
journal={IEICE TRANSACTIONS on Communications},
title={3D Facial Modelling for Model-Based Coding},
year={1993},
volume={E76-B},
number={6},
pages={626-633},
abstract={We describe an approach for modelling a person's face for model-based coding. The goal is to estimate the 3D shape by combining the contour analysis and shading analysis of the human face image in order to increase the quality of the estimated 3D shape. The motivation for combining contour and shading cues comes from the observation that the shading cue leads to severe errors near the occluding boundary, while the occluding contour cue provides incomplete surface information in regions away from contours. Towards this, we use the deformable model as the common level of integration such that a higher-quality measurement will dominate the depth estimate. The feasibility of our approach is demonstrated using a real facial image.},
keywords={},
doi={},
ISSN={},
month={June},}
Copy
TY - JOUR
TI - 3D Facial Modelling for Model-Based Coding
T2 - IEICE TRANSACTIONS on Communications
SP - 626
EP - 633
AU - Hiroyuki MORIKAWA
AU - Eiji KONDO
AU - Hiroshi HARASHIMA
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Communications
SN -
VL - E76-B
IS - 6
JA - IEICE TRANSACTIONS on Communications
Y1 - June 1993
AB - We describe an approach for modelling a person's face for model-based coding. The goal is to estimate the 3D shape by combining the contour analysis and shading analysis of the human face image in order to increase the quality of the estimated 3D shape. The motivation for combining contour and shading cues comes from the observation that the shading cue leads to severe errors near the occluding boundary, while the occluding contour cue provides incomplete surface information in regions away from contours. Towards this, we use the deformable model as the common level of integration such that a higher-quality measurement will dominate the depth estimate. The feasibility of our approach is demonstrated using a real facial image.
ER -
English
