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

    Exploring deep features: deeper fully convolutional neural network for image segmentation

    Thumbnail
    View/Open
    13101176, 12201105 & 13101194_CSE.pdf (733.8Kb)
    Date
    2017-04-19
    Publisher
    BRAC University
    Author
    Kamran, Sharif Amit
    Bin Khaled, Md. Asif
    Bin Kabir, Sabit
    Metadata
    Show full item record
    URI
    http://hdl.handle.net/10361/8112
    Abstract
    Classification of images has been a widely regarded challenge for the past decade, but a new type of object recognition problem which deals with pixellevel segmentation is posing a more complex task for both computer vision enthusiasts and researcher alike. The convolutional neural network has become a staple for any recognition task, but a new type of ConvNet which is Fully convolutional in architecture has yielded more fine features and proponents. We propose a neural net where we take VGG19 [20], a well-known classification CNN, make it fully convolutional for extracting deeper features and lastly use skip-architectures[15] for getting finer output. This yields better result than the pre-existing FCN segmentation architecture [15, 25, 6]. Training was done on augmented VOC12 [4] with SBD [6]training data and validation set was used from reduced VOC12 validation dataset. The model scored mIOU of 68.1 percent in PASCAL VOC 2012 Segmentation challenge.
    Keywords
    Neural network; Image segmentation
     
    Description
    This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2017.
     
    Cataloged from PDF version of thesis report.
     
    Includes bibliographical references (page 31-33).
    Department
    Department of Computer Science and Engineering, BRAC University
    Collections
    • Thesis & Report, BSc (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