• DocumentCode
    250204
  • Title

    Expression: A dyadic conversation aid using Google Glass for people who are blind or visually impaired

  • Author

    Anam, Asm Iftekhar ; Alam, Shahinur ; Yeasin, Mohammed

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Univ. of Memphis, Memphis, TN, USA
  • fYear
    2014
  • fDate
    6-7 Nov. 2014
  • Firstpage
    57
  • Lastpage
    64
  • Abstract
    This paper presents `Expression´ - an integrated assistive solution using Google Glass. The key function of the system is to enable the user in perceiving social signals during a natural dyadic conversation. The design and implementation of the system addressed a number of technical and research challenges - video acquisition and communication over Wi-Fi, efficient detection and tracking of faces, overheating of Google Glass, robust detection of facial features and modeling behavioral expressions, and feedback system for perceiving social signals. Performance evaluation was conducted to ensure the completeness and generalizability of models. Furthermore, usability studies were performed with ten (10) subjects (six visually impaired and four blind-folded) to illustrate the utility of the `Expression´. Subjective evaluation of Expression was performed using a five (5) point Likert Scale and was found to be excellent (4.383).
  • Keywords
    face recognition; handicapped aids; object tracking; Expression; Google Glass; Wi-Fi; behavioral expression modeling; blind; dyadic conversation aid; face detection; face tracking; facial feature detection; feedback system; integrated assistive solution; model completeness; model generalizability; natural dyadic conversation; performance evaluation; social signals; video acquisition; video communication; visually impaired; Analytical models; Cameras; Computers; Context modeling; Glass; Google; Smart phones;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Mobile Computing, Applications and Services (MobiCASE), 2014 6th International Conference on
  • Conference_Location
    Austin, TX
  • Type

    conf

  • DOI
    10.4108/icst.mobicase.2014.257780
  • Filename
    7026278