Vision-based Korean Manual Alphabet recognition game for beginners

ABSTRACT

The Korean Manual Alphabet (KMA) corresponds to the vocabulary of Korean Sign Language (KSL) and people use this KMA when he/she spells each letter of a word such as a newly coined word without current body language in deaf society [1]. Hearing people usually does not know/understand KSL words, because he/she can use KMA in order to communicate simply with the deaf without learning complex sign languages. Min, et al developed the glove-based KMA recognition using blue-tooth [2]. In this paper, we propose the vision-based KMA recognition game interface using a low price Universal Serial Bus (USB) based camera. We aim to provide that beginners can learn KMA letters easily when playing game at the same time. In addition, the system is able to detect a user's hand from captured images and find out one Korean Alphabet (KA) falling letter in game that corresponds to a KMA letter. We evaluated capabilities of the proposed system in order to provide convenience and reliability to the users.

REFERENCES

• 1: Karen Nakamura, "Sign language," The Deaf Resource Library, http://www.deaflibrary.org/
• 2: Seungki Min, Sanghyuk Oh, Gyoryeong Kim, Taehyun Yoon, Yunli Lee, Keechul Jung, "Simple Glove-Based Korean Finger Spelling Recognition System", ICCSA 2007, LNCS, Vol. 4705/2007, pp. 1063--1073

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.10 Vision and Scene Understanding
            Subjects: Modeling and recovery of physical attributes

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)
          Subjects: Input devices and strategies (e.g., mouse, touchscreen)

  K. Computing Milieux
  K.8 PERSONAL COMPUTING
      K.8.0 General
          Subjects: Games

General Terms:
Design, Human Factors