Research Papers - Dept of Information Technology

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/593

Browse

Filters

2019 - 201912020 - 20221

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Convolutional neural networks

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationEmbargo
    EasyChat: A Chat Application for Deaf/Dumb People to Communicate with the General Community
    (Springer, Cham, 2022-07-07) Sriyaratna, D; Samararathne, W. A. H. K.; Gurusinghe, P. M.; Gunathilake, M. D. S. S.; Wijenayake, W. W. G. P. A.
    Sign Language is closely associated with the deaf and dumb community to communicate with each other. However, not everyone understands sign language or verbal languages, so these communities need proper ways to communicate online. Therefore, this paper presents EasyChat, a sign language chat application that can translate three main sign languages into Simple English text as well as Simple English text into sign language, which would benefit for deaf/dumb community to express their ideas with the general community by simply capturing their British Sign Language (BSL) or Makaton gestures/symbols or lip movements. These steps are handled by four components. The first component, Convert BSL into Simple English, and the second component, handles Lip Reading conversion. The Makaton gesture and symbol conversion component produces a simple English text-formatted output for identified Makaton hand signs. Finally, the Text/voice to Sign Converter works on converting entered English text back into the sign language-based images. By using these components, EasyChat can detect relevant gestures and lip movement inputs with superior accuracy and translate. This can lead to more effective and efficient online communication between the community of deaf/dumb individuals and the general public.
  • Thumbnail Image
    PublicationEmbargo
    Intelligent platform for visually impaired children for learning indoor and outdoor objects
    (IEEE, 2019-10-17) Jayawardena, C; Balasuriya, B. K; Lokuhettiarachchi, N. P; Ranasinghe, A. R. M. D. N
    Using Artificial Intelligence and Computer Vision to assist Visually Impaired personal has been a topic discussed in recent years. Many researchers are focusing on combining several technologies to assist said individuals to perform day to day tasks. Although there are already many technologies being used as platforms to help these individuals, focus put on children who are aged in between 6 - 14 years is considerably less. Therefore; in this research we are focusing on how to use latest advancements of Region Based Convolutional Networks (R-CNN), Recurrent Neural Networks (RNN) and Speech models to provide an interactive learning experience to visually impaired children.