• Login
    • Library Home
    View Item 
    •   BracU IR
    • School of Engineering and Computer Science (SECS)
    • Department of Computer Science and Engineering (CSE)
    • Thesis & Report, MSc (Computer Science and Engineering)
    • View Item
    •   BracU IR
    • School of Engineering and Computer Science (SECS)
    • Department of Computer Science and Engineering (CSE)
    • Thesis & Report, MSc (Computer Science and Engineering)
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    A viseme recognition system using lip curvature and neural networks to detect Bangla vowels

    Thumbnail
    View/Open
    14166001_MSc in CSE.pdf (1.501Mb)
    Date
    2016
    Publisher
    BRAC Univeristy
    Author
    Akhter, Nahid
    Metadata
    Show full item record
    URI
    http://hdl.handle.net/10361/8366
    Abstract
    Automatic Speech Recognition plays an important role in human-computer interaction, which can be applied in various vital applications like crime-fighting and helping the hearing-impaired. It consists of two domains – Audio Speech Recognition and Visual Speech Recognition. This thesis is based on Recognition of Speech in the visual domain only, i.e. it involves recognizing speech without the presence or support of any auditory signal. So far, a lot of research has been done on lip-reading in English and some amount on French and Chinese, as well as few other languages, but not much research has been done on lip-reading in Bengali. This thesis work provides a new approach to lip reading Bengali vowels using a combination of the curvature of the inner and outer lips and Neural Networks. The method uses a more robust and faster algorithm to detect the lip contour than conventional methods used so far, such as Active Contour Model, Active Appearance Model and Active Shape Models. The method used for feature extraction is also new. It makes use of coefficients of the curves of the inner and outer lips. This way, it makes use of a lesser number of parameters to represent the shape of the lip when pronouncing a vowel. Moreover, the method is also robust to alignment of lips at different angles and can work with low resolution pictures also. Finally, for recognition of the viseme, a Backpropagation Neural Network is trained and simulated using gradient descent method.
    Keywords
    Neural network; Lip curvature; Viseme recognition
     
    Description
    This thesis report is submitted in partial fulfilment of the requirements for the degree of Master of Science in Computer Science and Engineering, 2016.
     
    Cataloged from PDF version of thesis report.
     
    Includes bibliographical references (page 46-50).
    Department
    Department of Computer Science and Engineering, BRAC University
    Collections
    • Thesis & Report, MSc (Computer Science and Engineering)

    Copyright © 2008-2019 Ayesha Abed Library, Brac University 
    Contact Us | Send Feedback
     

     

    Policy Guidelines

    • BracU Policy
    • Publisher Policy

    Browse

    All of BracU Institutional RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage Statistics

    Copyright © 2008-2019 Ayesha Abed Library, Brac University 
    Contact Us | Send Feedback