Title :
Korean Manual Alphabet (KMA) Recognition for Composition of a Korean Syllable Character
Author :
Oh, Young-Joon ; Park, Kwang-Hyun ; Bien, Zeungnam
Author_Institution :
Korea Adv. Inst. of Sci. & Technol., Daejeon
Abstract :
Sign language is complex visual-spatial language most used in deaf society, and is a representative example of hand gesture with linguistic structure. Korean manual alphabet is a manual alphabet that expresses the vowel and the consonant of Korean sign language. This paper presents a system which recognizes the Korean manual alphabet (KMA) using a USB camera and translates into a normal Korean character. The system captures images from a camera and extracts skin color region from an image, and finds a hand region. The system detects a skin colored hand without particular cloth in a complex background. We use 33 KMA hand shapes as template images, and the system compares hand shape with template images using a correlation coefficient method and composes a text syllable of initial consonant, medial vowel and final consonant.
Keywords :
character recognition; feature extraction; gesture recognition; image colour analysis; image sensors; Korean manual alphabet recognition; Korean sign language; Korean syllable character; consonant; correlation coefficient method; sign language; template images; text syllable; visual-spatial language; vowel; Cameras; Character recognition; Deafness; Handicapped aids; Hidden Markov models; Information technology; Natural languages; Shape; Skin; Universal Serial Bus;
Conference_Titel :
Convergence Information Technology, 2007. International Conference on
Conference_Location :
Gyeongju
Print_ISBN :
0-7695-3038-9
DOI :
10.1109/ICCIT.2007.13
