Text-driven automatic frame generation using MPEG-4 Synthetic/Natural Hybrid Coding for 2-D head-and-shoulder scene

Chun-Ho Cheung; Lai-Man Po

doi:10.1109/ICIP.1997.638675

Text-driven automatic frame generation using MPEG-4 Synthetic/Natural Hybrid Coding for 2-D head-and-shoulder scene

Chun-Ho Cheung^*
, Lai-Man Po

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

In this paper, we propose a facial modeling technique based on the MPEG-4 Synthetic/Natural Hybrid Coding for automating frame sequence generation of a talking head. With the definition and animation parameters on a generic face object, the shape, textures and expressions of an adapted frontal face can generally be controlled and synchronized by the phonemes transcribed from plain text. By this developed facial modeling technique, it increases the intelligibility of an non-verbal facial communication for potential audiovisual lip-synch application on news reporting, lip-reading for the hearing-impaired or the deaf, virtual meeting through internet, and Story Teller on Demand (STOD). © 1997 IEEE

Original language	English
Title of host publication	Proceedings International Conference On Image Processing
Publisher	IEEE
Pages	69-72
Volume	2
ISBN (Print)	0-8186-8183-7
DOIs	https://doi.org/10.1109/ICIP.1997.638675
Publication status	Published - Oct 1997
Event	1997 International Conference on Image Processing - Santa Barbara, CA, United States Duration: 26 Oct 1997 → 29 Oct 1997

Conference

Conference	1997 International Conference on Image Processing
Place	United States
City	Santa Barbara, CA
Period	26/10/97 → 29/10/97

Access Output

10.1109/ICIP.1997.638675

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{524d0cef6e934ebaa18d414abb2f014a,

title = "Text-driven automatic frame generation using MPEG-4 Synthetic/Natural Hybrid Coding for 2-D head-and-shoulder scene",

abstract = "In this paper, we propose a facial modeling technique based on the MPEG-4 Synthetic/Natural Hybrid Coding for automating frame sequence generation of a talking head. With the definition and animation parameters on a generic face object, the shape, textures and expressions of an adapted frontal face can generally be controlled and synchronized by the phonemes transcribed from plain text. By this developed facial modeling technique, it increases the intelligibility of an non-verbal facial communication for potential audiovisual lip-synch application on news reporting, lip-reading for the hearing-impaired or the deaf, virtual meeting through internet, and Story Teller on Demand (STOD). {\textcopyright} 1997 IEEE ",

author = "Chun-Ho Cheung and Lai-Man Po",

year = "1997",

month = oct,

doi = "10.1109/ICIP.1997.638675",

language = "English",

isbn = "0-8186-8183-7",

volume = "2",

pages = "69--72",

booktitle = "Proceedings International Conference On Image Processing",

publisher = "IEEE",

address = "United States",

note = "1997 International Conference on Image Processing ; Conference date: 26-10-1997 Through 29-10-1997",

}

Text-driven automatic frame generation using MPEG-4 Synthetic/Natural Hybrid Coding for 2-D head-and-shoulder scene. / Cheung, Chun-Ho; Po, Lai-Man.
Proceedings International Conference On Image Processing. Vol. 2 IEEE, 1997. p. 69-72.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Text-driven automatic frame generation using MPEG-4 Synthetic/Natural Hybrid Coding for 2-D head-and-shoulder scene

AU - Cheung, Chun-Ho

AU - Po, Lai-Man

PY - 1997/10

Y1 - 1997/10

N2 - In this paper, we propose a facial modeling technique based on the MPEG-4 Synthetic/Natural Hybrid Coding for automating frame sequence generation of a talking head. With the definition and animation parameters on a generic face object, the shape, textures and expressions of an adapted frontal face can generally be controlled and synchronized by the phonemes transcribed from plain text. By this developed facial modeling technique, it increases the intelligibility of an non-verbal facial communication for potential audiovisual lip-synch application on news reporting, lip-reading for the hearing-impaired or the deaf, virtual meeting through internet, and Story Teller on Demand (STOD). © 1997 IEEE

AB - In this paper, we propose a facial modeling technique based on the MPEG-4 Synthetic/Natural Hybrid Coding for automating frame sequence generation of a talking head. With the definition and animation parameters on a generic face object, the shape, textures and expressions of an adapted frontal face can generally be controlled and synchronized by the phonemes transcribed from plain text. By this developed facial modeling technique, it increases the intelligibility of an non-verbal facial communication for potential audiovisual lip-synch application on news reporting, lip-reading for the hearing-impaired or the deaf, virtual meeting through internet, and Story Teller on Demand (STOD). © 1997 IEEE

UR - https://www.scopus.com/pages/publications/0031377768

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0031377768&origin=recordpage

U2 - 10.1109/ICIP.1997.638675

DO - 10.1109/ICIP.1997.638675

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0-8186-8183-7

VL - 2

SP - 69

EP - 72

BT - Proceedings International Conference On Image Processing

PB - IEEE

T2 - 1997 International Conference on Image Processing

Y2 - 26 October 1997 through 29 October 1997

ER -

Text-driven automatic frame generation using MPEG-4 Synthetic/Natural Hybrid Coding for 2-D head-and-shoulder scene

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this