Synthesis of image sequences for Korean sign language using 3D shape model

Mun-Ho Hong; Chang-Seok Choi; Chang-Seok Kim; Joon-Hyeon Jeon

doi:10.1117/12.209654

30 May 1995 Synthesis of image sequences for Korean sign language using 3D shape model

Mun-Ho Hong, Chang-Seok Choi, Chang-Seok Kim, Joon-Hyeon Jeon

Proceedings Volume 2513, 21st International Congress on: High-Speed Photography and Photonics; (1995) https://doi.org/10.1117/12.209654
Event: High-Speed Photography and Photonics: 21st International Congress, 1994, Taejon, Korea, Republic of

Abstract

This paper proposes a method for offering information and realizing communication to the deaf-mute. The deaf-mute communicates with another person by means of sign language, but most people are unfamiliar with it. This method enables to convert text data into the corresponding image sequences for Korean sign language (KSL). Using a general 3D shape model of the upper body leads to generating the 3D motions of KSL. It is necessary to construct the general 3D shape model considering the anatomical structure of the human body. To obtain a personal 3D shape model, this general model is to adjust to the personal base images. Image synthesis for KSL consists of deforming a personal 3D shape model and texture-mapping the personal images onto the deformed model. The 3D motions for KSL have the facial expressions and the 3D movements of the head, trunk, arms and hands and are parameterized for easily deforming the model. These motion parameters of the upper body are extracted from a skilled signer's motion for each KSL and are stored to the database. Editing the parameters according to the inputs of text data yields to generate the image sequences of 3D motions.

Citation Download Citation

Mun-Ho Hong, Chang-Seok Choi, Chang-Seok Kim, and Joon-Hyeon Jeon "Synthesis of image sequences for Korean sign language using 3D shape model", Proc. SPIE 2513, 21st International Congress on: High-Speed Photography and Photonics, (30 May 1995); https://doi.org/10.1117/12.209654

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available