Volume 22, Issue 13 pp. 59-69
Article
Full Access

A realtime model-based facial image synthesis based on multiprocessor network

Shigeo Morishima

Shigeo Morishima

Faculty of Engineering, Seikei University, Musashino, Japan 180

Shigeo Morishima graduated in 1982 from the Electronics Department, Faculty of Engineering, University of Tokyo, where he obtained a Master's degree in 1984 and a Dr. of Eng. degree in 1987. He was appointed Lecturer in theElectrical Engineering Department, Faculty of Engineering, Seikei University, the same year and has been an Associate Professor since 1988. He has been engaged in research onintelligence engineering, speech-signal processing, image processing, and media conversion of speech and image. He is a member of IEEE; the Institute of Image Processing, Japan; the Acoustical Society of Japan; and the Institute of Information Theory, Japan.

Search for more papers by this author
Seiji Kobayashi

Seiji Kobayashi

Faculty of Engineering, Seikei University, Musashino, Japan 180

Seiji Kobayashi graduated in 1989 from the Electrical Engineering Department, Faculty of Engineering, Seikei University. While in the Master's program at the University, he engaged in research on intelligent image coding and parallel image processors.

Search for more papers by this author
Hiroshi Harashima

Hiroshi Harashima

Faculty of Engineering, The University of Tokyo, Tokyo, Japan 113

Hiroshi Harashima graduated in 1968 from the Electronics Engineering Department, Faculty of Engineering, University of Tokyo, obtained aDr. of Eng. degree from there in 1973, and then was appointed Lecturer of Electrical Engineering. Presently, he works at theSogo Shikenjo of the Engineering Department of thesame University. He was a guest researcher at Stanford University (USA) in 1959. He hasbeen engaged in research on communication theory, coding theory, communication systems such as high-efficiency digital modulatioddemodulation systems, image coding and processing, and digital-signal processingand its medical applications. He was awarded the Yonezawa Prize in 1973, and the Achievement Award of the I.E.C.E., Japan, in 1979. He isa co-author of books such as DigitalCommunication Zheory and Itrfortriarion Coding Theory. He is a member of IEEE; member and a secretary of I.E.E., Japan, and the Japanese Institute of Medical Engineering; anda member of the board of the Institute of BrainwaveEMG, Japan.

Search for more papers by this author
First published: 1991
Citations: 1

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.

The full text of this article hosted at iucr.org is unavailable due to technical difficulties.