한국지능시스템학회:학술대회논문집 (Proceedings of the Korean Institute of Intelligent Systems Conference)
- 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
- /
- Pages.333-336
- /
- 1996
한글 수화 및 지화의 실시간 인식 시스템 구현
Ral-time Recognition of Continuous KSL & KMA using Automata and Fuzzy Techniques
- 이찬수 (한국과학기술원 전기 및 전자공학과) ;
- 김종성 (한국과학기술원 전기 및 전자공학과) ;
- 박규태 (한국과학기술원 전기 및 전자공학과) ;
- 변증남 (한국과학기술원 전기 및 전자공학과) ;
- 장원 (국방 과학 연구소) ;
- 김성권 (삼성 전자 기술 총괄 생산 기술 연구소)
- Lee, Chan-Su (Department of Electrical Engineering, KAIST) ;
- Kim, Jong-Sung (Department of Electrical Engineering, KAIST) ;
- Park, Gyu-Tae (Department of Electrical Engineering, KAIST) ;
- Bien, Zeung-Nam (Department of Electrical Engineering, KAIST) ;
- Jang, Won (Agency for Defense Development) ;
- Kim, Sung-Kwon (Samsung Electronics Co. LTD)
- 발행 : 1996.10.01
초록
The sign language is a method of communication for deaf person. For sign communication, sign language and manual alphabet are used continuously. In this paper is proposed a system which recognize Korean sign language(KSL) and Korean manual alphabet(KMA) continuously. For recognizing KSL and KMA, basic elements for sign language, namely, the 14 hand directions, 23 hand postures, and 14 hand orientations are used. At first, this system recognize current motion state using speed and change of speed in motion by state automata. Using state, basic element classifiers using Fuzzy Min-Max Neural Network and Fuzzy Rule are executed. Meaning of signed gesture is selected by using basic elements which was recognized.
키워드