Type of blur and blur parameters identification using neural network and its application to image restoration

被引：0
|
作者：
Aizenberg, I [1 ]
Bregin, T [1 ]
Butakoff, C [1 ]
Karnaukhov, V [1 ]
Merzlyakov, N [1 ]
Milukova, O [1 ]
机构：
[1] Russian Acad Sci, Inst Informat Transmiss Problems, Moscow 117901, Russia
来源：
ARTIFICIAL NEURAL NETWORKS - ICANN 2002 | 2002年 / 2415卷
关键词：
neural network; image restoration; frequency domain;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The original solution of the blur and blur parameters identification problem is presented in this paper. A neural network based on multi-valued neurons is used for the blur and blur parameters identification. It is shown that using simple single-layered neural network-it is possible to identify the type of the distorting operator. Four types of blur are considered: defocus, rectangular, motion and Gaussian ones. The parameters of the corresponding operator are identified using a similar neural network. After a type of blur and its parameters identification the image can be restored using several kinds of methods.
引用
收藏
页码：1231 / 1236
页数：6
相关论文
共 50 条
  • [41] Blur Identification of the Degraded Images Based on Convolutional Neural Network
    Huang, Yilin
    Gao, Fei
    2019 4TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND APPLICATIONS (ICCIA 2019), 2019, : 63 - 67
  • [42] Study on Motion blur image restoration algorithms
    Fan, Yu
    Wu, Xuefeng
    MATERIALS PROCESSING AND MANUFACTURING III, PTS 1-4, 2013, 753-755 : 2976 - 2979
  • [43] Motion blur in fluoroscopy: effects, identification and restoration
    Mayntz, C
    Aach, T
    Kunz, D
    Frahm, JM
    MEDICAL IMAGING 2000: IMAGE PROCESSING, PTS 1 AND 2, 2000, 3979 : 618 - 629
  • [44] SINGLE IMAGE LOCAL BLUR IDENTIFICATION
    Trouve, P.
    Champagnat, F.
    Le Besnerais, G.
    Idier, J.
    2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011, : 613 - 616
  • [45] Image Forgery Detection Based on Motion Blur Estimated Using Convolutional Neural Network
    Song, Chunhe
    Zeng, Peng
    Wang, Zhongfeng
    Li, Tong
    Qiao, Lin
    Shen, Li
    IEEE SENSORS JOURNAL, 2019, 19 (23) : 11601 - 11611
  • [46] Identification of blur support size in blind image restoration with moderate/intense noise
    Zhang Chunxiao
    Zhao Yan
    Xu Dong
    SEVENTH INTERNATIONAL SYMPOSIUM ON INSTRUMENTATION AND CONTROL TECHNOLOGY: OPTOELECTRONIC TECHNOLOGY AND INSTUMENTS, CONTROL THEORY AND AUTOMATION, AND SPACE EXPLORATION, 2008, 7129
  • [47] A SVM-based blur identification algorithm for image restoration and resolution enhancement
    Qiao, Jianping
    Liu, Ju
    KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 2, PROCEEDINGS, 2006, 4252 : 28 - 35
  • [48] Motion Blur Parameters Identification from Radon Transform Image Gradients
    Sun, Hongwei
    Desvignes, Michel
    Yan, Yunhui
    Liu, Weiwei
    IECON: 2009 35TH ANNUAL CONFERENCE OF IEEE INDUSTRIAL ELECTRONICS, VOLS 1-6, 2009, : 1973 - +
  • [49] Blurred Image Restoration using Fast Blur-Kernel Estimation
    Huang, Hui-Yu
    Tsai, Wei-Chang
    2014 TENTH INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATION HIDING AND MULTIMEDIA SIGNAL PROCESSING (IIH-MSP 2014), 2014, : 435 - 438
  • [50] Out-of-Focus Blur Image Restoration using the Akamatsu Transform
    Karungaru, Stephen
    Sugizaki, Masakazu
    Fukumi, Minoru
    Mitsukura, Yasue
    Akamatsu, Norio
    IECON: 2009 35TH ANNUAL CONFERENCE OF IEEE INDUSTRIAL ELECTRONICS, VOLS 1-6, 2009, : 4044 - +
12345