DSpace Repository

Browsing Elektrik Elektronik Mühendisliği Bölümü by Subject "Deep Features"

Browsing Elektrik Elektronik Mühendisliği Bölümü by Subject "Deep Features"

Sort by: Order: Results:

  • A Hybrid Framework for Matching Printing Design Files to Product Photos 
    Kaplan, Alper; Akagündüz, Erdem (2020)
    We propose a real-time image matching framework, which is hybrid in the sense that it uses both hand-crafted features and deep features obtained from a well-tuned deep convolutional network. The matching problem, which we ...
  • Defining Image Memorability Using the Visual Memory Schema 
    Akagündüz, Erdem; Bors, Adrian G.; Evans, Karla K. (2020-09-01)
    Memorability of an image is a characteristic determined by the human observers' ability to remember images they have seen. Yet recent work on image memorability defines it as an intrinsic property that can be obtained ...