• Login
    View Item 
    •   eScholar Home
    • Faculty of Science
    • Master Theses & Projects
    • View Item
    •   eScholar Home
    • Faculty of Science
    • Master Theses & Projects
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Multi-character prediction using attention

    Thumbnail
    View/Open
    Baeenh_Mohmmed.pdf (10.62Mb)
    Date
    2020-01-01
    Author
    Baeenh, Mohmmed
    Metadata
    Show full item record
    Abstract
    We propose a computational attention approach to localize and classify characters in a sequence in a given image. Our approach combines spatial soft-attention with attention regularization and learns “where-to-look” to carry out the sequence classification task. The image is first passed through a Convolutional Neural Network (CNN) that serves as feature extractor. Then at each Recurrent Neural Network (RNN) time step, the attention mechanism attends to the relevant features sequentially to make predictions. The attention mechanism also includes a start and stop state, which instructs the mechanism to start looking and guides it when to stop (e.g., when the sequence has been exhausted). We demonstrate our approach on two sequence detection tasks—multi-digit classification and CAPTCHA unlocking—using the publicly available Street View House Numbers (SVHN) dataset and a custom CAPTCHA dataset. The experiments confirm our hypothesis that the network learns to attend to relevant features by minimizing the loss between the ground truth attention masks and the predicted attention masks.
    URI
    https://hdl.handle.net/10155/1132
    Collections
    • Electronic Theses and Dissertations [1323]
    • Master Theses & Projects [292]

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of eScholarCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV