• Login
    View Item 
    •   DSpace Home
    • Stony Brook University
    • Stony Brook Theses & Dissertations [SBU]
    • View Item
    •   DSpace Home
    • Stony Brook University
    • Stony Brook Theses & Dissertations [SBU]
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsDepartmentThis CollectionBy Issue DateAuthorsTitlesSubjectsDepartment

    My Account

    LoginRegister

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    High Level Describable Attributes for Predicting Aesthetics and Interestingness

    Thumbnail
    View/Open
    Dhar_grad.sunysb_0771M_10339.pdf (9.194Mb)
    Date
    1-Dec-10
    Author
    Dhar, Sagnik
    Publisher
    The Graduate School, Stony Brook University: Stony Brook, NY.
    Metadata
    Show full item record
    Abstract
    With the rise in popularity of digital cameras, the amount of visual data available on the web is growing exponentially. Some of these pictures are extremely beautiful and aesthetically pleasing. Unfortunately the vast majority are uninteresting or of low quality. This paper demonstrates a simple, yet powerful method to automatically select high aesthetic quality images from large image collections with performance significantly better than the state of the art. We also show significantly better results on predicting the interestingness of Flickr images, and on a novel problem of predicting query specific interestingness. Our aesthetic quality estimation method explicitly predicts some of the possible image cues that a human might use to evaluate an image and then uses them in a discriminative approach. These cues or high level describable image attributes fall into three broad types: 1) compositional attributes related to image layout or configuration, 2) content attributes related to the objects or scene types depicted, and 3) sky-illumination attributes related to the natural lightingconditions. We demonstrate that an aesthetics classifier trained on these describable attributes can provide a significant improvement over state of the art methods for predicting human quality judgments.
    URI
    http://hdl.handle.net/1951/55408
    Collections
    • Stony Brook Theses & Dissertations [SBU] [1955]

    SUNY Digital Repository Support
    DSpace software copyright © 2002-2023  DuraSpace
    Contact Us | Send Feedback
    DSpace Express is a service operated by 
    Atmire NV
     

     


    SUNY Digital Repository Support
    DSpace software copyright © 2002-2023  DuraSpace
    Contact Us | Send Feedback
    DSpace Express is a service operated by 
    Atmire NV