English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62793/95819 (66%)
Visitors : 3638574      Online Users : 403
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/117397


    Title: Residual Learning Based Convolutional Neural Network for Super Resolution
    Authors: Lin, Hwei Jen;Tokuyama, Yoshimasa;Lin, Zi-Jun
    Keywords: super resolution;convolutional networks;bicubic interpolation;deep learning;underdetermined inverse problem
    Date: 2019-07-07
    Issue Date: 2019-10-15 12:11:34 (UTC+8)
    Abstract: Recently, there have been many methods of super resolution proposed in the literature, in which convolutional neural networks have been confirmed to achieve good results. C. Dong et al. proposed a convolutional neural network structure (SRCNN) to effectively solve the super resolution problem. J. Kim et al. proposed a much deeper convolutional neural network (VDSR) to improve C. Dong et al.’s method. However, unlike VDSR proposed by J. Kim et al. which trained residue images, SRCNN proposed by C. Dong et al. directly trained high-resolution images. Consequently, we surmise the improvement of VDSR is due to not only to the depth of the neural network structure but also the training of residue images. This paper studies and compares the performance of training high-resolution images and training residue images associated with the two neural network structures, SRCNN and VDSR. Some deep CNNs proceed zero padding which pads the input to each convolutional layer with zeros around the border so the feature maps remain the same size. SRCNN proposed by C. Dong et al. does not carry out padding, so the size of the resulting high-resolution images is smaller than expected. The study also proposes two revised versions of SRCNN that remain the size the same as the input image.
    Relation: Proceedings of 2019 International Electronics Communication Conference
    Appears in Collections:[Graduate Institute & Department of Computer Science and Information Engineering] Proceeding

    Files in This Item:

    File SizeFormat
    index.html0KbHTML178View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback