CLASSIFYING DEGRADED IMAGES OVER VARIOUS LEVELS OF DEGRADATION

被引：0
作者：
Endo, Kazuki [1 ]
Tanaka, Masayuki [1 ,2 ]
Okutomi, Masatoshi [1 ]
机构：
[1] Tokyo Inst Technol, Tokyo, Japan
[2] Natl Inst Adv Ind Sci & Technol, Tsukuba, Ibaraki, Japan
来源：
2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2020年
关键词：
Degraded Image; Classification; Convolutional Neural Network; Ensemble; Restoration;
D O I：
10.1109/icip40778.2020.9191087
中图分类号：
TB8 [摄影技术];
学科分类号：
0804 ;
摘要：
Classification for degraded images having various levels of degradation is very important in practical applications. This paper proposes a convolutional neural network to classify degraded images by using a restoration network and an ensemble learning. The results demonstrate that the proposed network can classify degraded images over various levels of degradation well. This paper also reveals how the image-quality of training data for a classification network affects the classification performance of degraded images.
引用
收藏
页码：1691 / 1695
页数：5
相关论文
共 28 条
  • [1] [Anonymous], 2009, Technical report
  • [2] [Anonymous], 2015, P 3 INT C LEARN REPR
  • [3] Convolutional low-resolution fine-grained classification
    Cai, Dingding
    Chen, Ke
    Qian, Yanlin
    Kamarainen, Joni-Kristian
    [J]. PATTERN RECOGNITION LETTERS, 2019, 119 : 166 - 171
  • [4] Learning a Deep Convolutional Network for Image Super-Resolution
    Dong, Chao
    Loy, Chen Change
    He, Kaiming
    Tang, Xiaoou
    [J]. COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 : 184 - 199
  • [5] Shared Address Translation Revisited
    Dong, Xiaowan
    Dwarkadas, Sandhya
    Cox, Alan L.
    [J]. PROCEEDINGS OF THE ELEVENTH EUROPEAN CONFERENCE ON COMPUTER SYSTEMS, (EUROSYS 2016), 2016,
  • [6] Endo K., 2020, P IS T INT S EL IM, P1
  • [7] Ghosh S, 2018, 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), P2916, DOI 10.1109/ICASSP.2018.8461907
  • [8] Identity Mappings in Deep Residual Networks
    He, Kaiming
    Zhang, Xiangyu
    Ren, Shaoqing
    Sun, Jian
    [J]. COMPUTER VISION - ECCV 2016, PT IV, 2016, 9908 : 630 - 645
  • [9] Deep Residual Learning for Image Recognition
    He, Kaiming
    Zhang, Xiangyu
    Ren, Shaoqing
    Sun, Jian
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 770 - 778
  • [10] Huang JB, 2015, PROC CVPR IEEE, P5197, DOI 10.1109/CVPR.2015.7299156
123