Realtime model-based facial image synthesis based on multiprocessor network

Shigeo Morishima, Seiji Kobayashi, Hiroshi Harashima

Research output: Contribution to journalArticle

Abstract

Model-based image coding has been highlighted recently as a high-efficiency coding method for TV telephone and TV conference systems. In a model-based coding system, an ultralow-rate image transmission is realized by obtaining common models of a facial image at both sides of a communication and by transmitting only modification parameters between them. However, it is difficult to realize a realtime processing of a model-based coding with a conventional iterative-processing type computer since the amount of material to analyze and synthesize at both sides is very large. Realtime processing is absolutely necessary to realize a practical system using this method, i.e., highspeed processings at both the transmitter and receiver are required. This paper describes a realtime facial image synthesis method based on a multiprocessor construction with a transputer. The transputer is a microcomputer having a communication capability with multiple processors and 10 MIPS CPU performance. Using this system in a pipeline processing with 20 processors, it is possible to synthesize realtime facial images at a rate of about 16 frames per second. If only a part around the lips is transmitted, it is possible to synthesize an image at a rate of about 40 frames per second with a network using five processors.

Original languageEnglish
Pages (from-to)59-69
Number of pages11
JournalSystems and Computers in Japan
Volume22
Issue number13
Publication statusPublished - 1991
Externally publishedYes

Fingerprint

Multiprocessor
Real-time Processing
Synthesis
Transputers
Model-based
Real-time
Coding
Processing
Program processors
Image Transmission
Image Coding
Microcomputer
Image communication systems
Transmitter
Communication
High Efficiency
High Speed
Image coding
Receiver
Telephone

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science

Cite this

Realtime model-based facial image synthesis based on multiprocessor network. / Morishima, Shigeo; Kobayashi, Seiji; Harashima, Hiroshi.

In: Systems and Computers in Japan, Vol. 22, No. 13, 1991, p. 59-69.

Research output: Contribution to journalArticle

Morishima, Shigeo ; Kobayashi, Seiji ; Harashima, Hiroshi. / Realtime model-based facial image synthesis based on multiprocessor network. In: Systems and Computers in Japan. 1991 ; Vol. 22, No. 13. pp. 59-69.
@article{3133751aa90346ae8649970f513619db,
title = "Realtime model-based facial image synthesis based on multiprocessor network",
abstract = "Model-based image coding has been highlighted recently as a high-efficiency coding method for TV telephone and TV conference systems. In a model-based coding system, an ultralow-rate image transmission is realized by obtaining common models of a facial image at both sides of a communication and by transmitting only modification parameters between them. However, it is difficult to realize a realtime processing of a model-based coding with a conventional iterative-processing type computer since the amount of material to analyze and synthesize at both sides is very large. Realtime processing is absolutely necessary to realize a practical system using this method, i.e., highspeed processings at both the transmitter and receiver are required. This paper describes a realtime facial image synthesis method based on a multiprocessor construction with a transputer. The transputer is a microcomputer having a communication capability with multiple processors and 10 MIPS CPU performance. Using this system in a pipeline processing with 20 processors, it is possible to synthesize realtime facial images at a rate of about 16 frames per second. If only a part around the lips is transmitted, it is possible to synthesize an image at a rate of about 40 frames per second with a network using five processors.",
author = "Shigeo Morishima and Seiji Kobayashi and Hiroshi Harashima",
year = "1991",
language = "English",
volume = "22",
pages = "59--69",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "13",

}

TY - JOUR

T1 - Realtime model-based facial image synthesis based on multiprocessor network

AU - Morishima, Shigeo

AU - Kobayashi, Seiji

AU - Harashima, Hiroshi

PY - 1991

Y1 - 1991

N2 - Model-based image coding has been highlighted recently as a high-efficiency coding method for TV telephone and TV conference systems. In a model-based coding system, an ultralow-rate image transmission is realized by obtaining common models of a facial image at both sides of a communication and by transmitting only modification parameters between them. However, it is difficult to realize a realtime processing of a model-based coding with a conventional iterative-processing type computer since the amount of material to analyze and synthesize at both sides is very large. Realtime processing is absolutely necessary to realize a practical system using this method, i.e., highspeed processings at both the transmitter and receiver are required. This paper describes a realtime facial image synthesis method based on a multiprocessor construction with a transputer. The transputer is a microcomputer having a communication capability with multiple processors and 10 MIPS CPU performance. Using this system in a pipeline processing with 20 processors, it is possible to synthesize realtime facial images at a rate of about 16 frames per second. If only a part around the lips is transmitted, it is possible to synthesize an image at a rate of about 40 frames per second with a network using five processors.

AB - Model-based image coding has been highlighted recently as a high-efficiency coding method for TV telephone and TV conference systems. In a model-based coding system, an ultralow-rate image transmission is realized by obtaining common models of a facial image at both sides of a communication and by transmitting only modification parameters between them. However, it is difficult to realize a realtime processing of a model-based coding with a conventional iterative-processing type computer since the amount of material to analyze and synthesize at both sides is very large. Realtime processing is absolutely necessary to realize a practical system using this method, i.e., highspeed processings at both the transmitter and receiver are required. This paper describes a realtime facial image synthesis method based on a multiprocessor construction with a transputer. The transputer is a microcomputer having a communication capability with multiple processors and 10 MIPS CPU performance. Using this system in a pipeline processing with 20 processors, it is possible to synthesize realtime facial images at a rate of about 16 frames per second. If only a part around the lips is transmitted, it is possible to synthesize an image at a rate of about 40 frames per second with a network using five processors.

UR - http://www.scopus.com/inward/record.url?scp=0026399893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026399893&partnerID=8YFLogxK

M3 - Article

VL - 22

SP - 59

EP - 69

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 13

ER -