3D reconstruction from a single image for a Chinese talking face

Ning Liu, Ning Fang, Seiichiro Kamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper proposes an automatic 3D reconstruction approach for a Chinese talking face by a generic model and a single image. Firstly, an improved color-based ASM method is used to detect the face area and get the 2D face feature points automatically from the given image, which is not restricted to full frontal one. Then, color information is used to correct the location of face feature points. Finally, after text mapping, a particular and realistic 3D face model is deformed from a generic model. Using ASM face feature points extraction and correction based on skin color model, the problem of side face information missing is successfully resolved. Depending on only one image and one generic model, the computing cost of memory and time is largely reduced. The 3D face reconstructed can be easily deformed to form different expressions and mouth shapes. Experiments show that this approach is fast and efficient and has an output of a lifelike Chinese talking face.

Original languageEnglish
Title of host publicationIEEE Region 10 Annual International Conference, Proceedings/TENCON
Pages1613-1616
Number of pages4
DOIs
Publication statusPublished - 2010
Event2010 IEEE Region 10 Conference, TENCON 2010 - Fukuoka
Duration: 2010 Nov 212010 Nov 24

Other

Other2010 IEEE Region 10 Conference, TENCON 2010
CityFukuoka
Period10/11/2110/11/24

Fingerprint

Color
Skin
Data storage equipment
Costs
Experiments

Keywords

  • 3D reconstruction
  • Feature points extraction
  • Skin model
  • Talking face
  • Texture mapping

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications

Cite this

Liu, N., Fang, N., & Kamata, S. (2010). 3D reconstruction from a single image for a Chinese talking face. In IEEE Region 10 Annual International Conference, Proceedings/TENCON (pp. 1613-1616). [5686036] https://doi.org/10.1109/TENCON.2010.5686036

3D reconstruction from a single image for a Chinese talking face. / Liu, Ning; Fang, Ning; Kamata, Seiichiro.

IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2010. p. 1613-1616 5686036.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, N, Fang, N & Kamata, S 2010, 3D reconstruction from a single image for a Chinese talking face. in IEEE Region 10 Annual International Conference, Proceedings/TENCON., 5686036, pp. 1613-1616, 2010 IEEE Region 10 Conference, TENCON 2010, Fukuoka, 10/11/21. https://doi.org/10.1109/TENCON.2010.5686036
Liu N, Fang N, Kamata S. 3D reconstruction from a single image for a Chinese talking face. In IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2010. p. 1613-1616. 5686036 https://doi.org/10.1109/TENCON.2010.5686036
Liu, Ning ; Fang, Ning ; Kamata, Seiichiro. / 3D reconstruction from a single image for a Chinese talking face. IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2010. pp. 1613-1616
@inproceedings{15665cc08e2c48ffbaf9e8d6ce1b58a5,
title = "3D reconstruction from a single image for a Chinese talking face",
abstract = "This paper proposes an automatic 3D reconstruction approach for a Chinese talking face by a generic model and a single image. Firstly, an improved color-based ASM method is used to detect the face area and get the 2D face feature points automatically from the given image, which is not restricted to full frontal one. Then, color information is used to correct the location of face feature points. Finally, after text mapping, a particular and realistic 3D face model is deformed from a generic model. Using ASM face feature points extraction and correction based on skin color model, the problem of side face information missing is successfully resolved. Depending on only one image and one generic model, the computing cost of memory and time is largely reduced. The 3D face reconstructed can be easily deformed to form different expressions and mouth shapes. Experiments show that this approach is fast and efficient and has an output of a lifelike Chinese talking face.",
keywords = "3D reconstruction, Feature points extraction, Skin model, Talking face, Texture mapping",
author = "Ning Liu and Ning Fang and Seiichiro Kamata",
year = "2010",
doi = "10.1109/TENCON.2010.5686036",
language = "English",
isbn = "9781424468904",
pages = "1613--1616",
booktitle = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

}

TY - GEN

T1 - 3D reconstruction from a single image for a Chinese talking face

AU - Liu, Ning

AU - Fang, Ning

AU - Kamata, Seiichiro

PY - 2010

Y1 - 2010

N2 - This paper proposes an automatic 3D reconstruction approach for a Chinese talking face by a generic model and a single image. Firstly, an improved color-based ASM method is used to detect the face area and get the 2D face feature points automatically from the given image, which is not restricted to full frontal one. Then, color information is used to correct the location of face feature points. Finally, after text mapping, a particular and realistic 3D face model is deformed from a generic model. Using ASM face feature points extraction and correction based on skin color model, the problem of side face information missing is successfully resolved. Depending on only one image and one generic model, the computing cost of memory and time is largely reduced. The 3D face reconstructed can be easily deformed to form different expressions and mouth shapes. Experiments show that this approach is fast and efficient and has an output of a lifelike Chinese talking face.

AB - This paper proposes an automatic 3D reconstruction approach for a Chinese talking face by a generic model and a single image. Firstly, an improved color-based ASM method is used to detect the face area and get the 2D face feature points automatically from the given image, which is not restricted to full frontal one. Then, color information is used to correct the location of face feature points. Finally, after text mapping, a particular and realistic 3D face model is deformed from a generic model. Using ASM face feature points extraction and correction based on skin color model, the problem of side face information missing is successfully resolved. Depending on only one image and one generic model, the computing cost of memory and time is largely reduced. The 3D face reconstructed can be easily deformed to form different expressions and mouth shapes. Experiments show that this approach is fast and efficient and has an output of a lifelike Chinese talking face.

KW - 3D reconstruction

KW - Feature points extraction

KW - Skin model

KW - Talking face

KW - Texture mapping

UR - http://www.scopus.com/inward/record.url?scp=79951633722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951633722&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2010.5686036

DO - 10.1109/TENCON.2010.5686036

M3 - Conference contribution

AN - SCOPUS:79951633722

SN - 9781424468904

SP - 1613

EP - 1616

BT - IEEE Region 10 Annual International Conference, Proceedings/TENCON

ER -