• About
  • Policies
  • What is openaccess
  • Library
  • Contact
Advanced search
      View Item 
      •   BUIR Home
      • University Library
      • Bilkent Theses
      • Theses - Department of Computer Engineering
      • Dept. of Computer Engineering - Master's degree
      • View Item
      •   BUIR Home
      • University Library
      • Bilkent Theses
      • Theses - Department of Computer Engineering
      • Dept. of Computer Engineering - Master's degree
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Image super-resolution using deep feedforward neural networks in spectral domain

      Thumbnail
      View / Download
      27.2 Mb
      Author
      Aydın, Onur
      Advisor
      Aksoy, Selim
      Date
      2018-03
      Publisher
      Bilkent University
      Language
      English
      Type
      Thesis
      Item Usage Stats
      243
      views
      145
      downloads
      Abstract
      With recent advances in deep learning area, learning machinery and mainstream approaches in computer vision research have changed dramatically from hardcoded features combined with classi ers to end-to-end trained deep convolutional neural networks (CNN) which give the state-of-the-art results in most of the computer vision research areas. Single-image super-resolution is one of these areas which are considerably in uenced by deep learning advancements. Most of the current state-of-the-art methods on super-resolution problem learn a nonlinear mapping from low-resolution images to high-resolution images in the spatial domain using consecutive convolutional layers in their network architectures. However, these state-of-the-art results are obtained by training a separate neural network architecture for each di erent scale factor. We propose a novel singleimage super-resolution system with the limited number of learning parameters in spectral domain in order to eliminate the necessity to train a separate neural network for each scale factor. As a spectral transform function which converts images from the spatial domain to the frequency domain, discrete cosine transform (DCT) which is a variant of discrete Fourier transform (DFT) is used. In addition, in the post-processing step, an artifact reduction module is added for removing ringing artifacts occurred due to spectral transformations. Even if the peak signal-to-noise ratio (PSNR) measurement of our super-resolution system is lower than current state-of-the-art methods, the spectral domain allows us to develop a single model with a single dataset for any scale factor and relatively obtain better structural similarity index (SSIM) results.
      Keywords
      Super-resolution
      Deep learning
      Fourier transform
      Permalink
      http://hdl.handle.net/11693/36341
      Collections
      • Dept. of Computer Engineering - Master's degree 511
      Show full item record

      Browse

      All of BUIRCommunities & CollectionsTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsThis CollectionTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartments

      My Account

      Login

      Statistics

      View Usage StatisticsView Google Analytics Statistics

      Bilkent University

      If you have trouble accessing this page and need to request an alternate format, contact the site administrator. Phone: (312) 290 1771
      Copyright © Bilkent University - Library IT

      Contact Us | Send Feedback | Off-Campus Access | Admin | Privacy