• DocumentCode
    2381087
  • Title

    Review in Sign Language Recognition Systems

  • Author

    Al-Ahdal, M. Ebrahim ; Tahir, Nooritawati Md

  • Author_Institution
    Centre for Comput. Eng., Univ. Teknol. MARA, Shah Alam, Malaysia
  • fYear
    2012
  • fDate
    18-20 March 2012
  • Firstpage
    52
  • Lastpage
    57
  • Abstract
    The Sign Language Recognition System (SLR) is highly desired due to its ability to overcome the barrier between deaf and hearing people. At present, a robust SLR is still unavailable in the real world due to numerous obstacles. Additionally, as we know, Sign Language recognition has emerged as one of the most important research areas in the field of human computer interaction (HCI). Hence, this paper presents an overview of the main research works based on the Sign Language recognition system, and the developed system classified into the sign capturing method and recognition techniques is discussed. The strengths and disadvantages that contribute to the system functioning perfectly or otherwise will be highlighted by invoking major problems associated with the developed systems. Next, a novel method for designing SLR system based on combining EMG sensors with a data glove is proposed. This method is based on electromyography signals recorded from hands muscles for allocating word boundaries for streams of words in continuous SLR. The proposed system is expected to resolve words segmentation problem, which will contribute to enhanced recognition capability for the continuous sign recognition system.
  • Keywords
    data gloves; electromyography; gesture recognition; handicapped aids; human computer interaction; EMG sensors; HCI; continuous SLR; continuous sign recognition system; data glove; electromyography signals; enhanced recognition capability; human computer interaction; robust SLR system; sign capturing method; sign language recognition system; word boundary allocation; word segmentation problem; word streams; Artificial neural networks; Electromyography; Feature extraction; Handicapped aids; Hidden Markov models; Muscles; Training; ANN; ASR; Data-glove; EMG; HMM;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computers & Informatics (ISCI), 2012 IEEE Symposium on
  • Conference_Location
    Penang
  • Print_ISBN
    978-1-4673-1685-9
  • Type

    conf

  • DOI
    10.1109/ISCI.2012.6222666
  • Filename
    6222666