Comparison of neural networks for suppression of multiplicative noise in images

被引:0
|
作者
Pavlov, V. A. [1 ]
Belov, A. A. [1 ]
Nguen, V. T. [1 ]
Jovanovski, N. [1 ]
Ovsyannikova, A. S. [1 ]
机构
[1] Peter Great St Petersburg Polytech Univ, Inst Elect & Telecommun, Polytech Skaya 29, St Petersburg 195251, Russia
关键词
speckle noise; radar image; SAR; noise reduction; image processing; neural network;
D O I
10.18287/2412-6179-CO-1400
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
The paper compares several neural network (NN) architectures for suppression of multiplicative noise. The images may contain sharp boundaries and large homogeneous areas. Convolutional and fully connected networks are investigated. It is shown that different architectures require significantly different amount of training data to reach the same noise suppression quality. Examples of NN requiring lower amounts of training data are presented.
引用
收藏
页码:425 / 432
页数:8
相关论文
共 50 条
  • [1] Speckle Noise Suppression in Ultrasound Images Using Modular Neural Networks
    Karthiha, G.
    Allwin, S.
    INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2023, 35 (02) : 1753 - 1765
  • [2] Application of convolutional neural networks trained on optical images for object detection in radar images
    Pavlov, V. A.
    Belov, A. A.
    Volvenko, S. V.
    Rashich, A., V
    COMPUTER OPTICS, 2024, 48 (02) : 253 - 259
  • [3] Neural networks for local recognition of images with mixed noise
    Dolia, AN
    Lukin, VV
    Zelensky, AA
    Astola, JT
    Anagnostopoulos, C
    APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN IMAGE PROCESSING VI, 2001, 4305 : 108 - 118
  • [4] Noise Reduction Technique for Images using Radial Basis Function Neural Networks
    Khowaja, Sander Ali
    Shah, Syed Zafi Sherhan
    Memon, Muhammad Usman
    MEHRAN UNIVERSITY RESEARCH JOURNAL OF ENGINEERING AND TECHNOLOGY, 2014, 33 (03) : 278 - 285
  • [5] A quantitative assessment of speckle noise reduction in SAR images using TLFFBP neural network
    Kalaiyarasi Murugesan
    Perumal Balasubramani
    Pallikonda Rajasekaran Murugan
    Arabian Journal of Geosciences, 2020, 13
  • [6] A quantitative assessment of speckle noise reduction in SAR images using TLFFBP neural network
    Murugesan, Kalaiyarasi
    Balasubramani, Perumal
    Rajasekaran, M. Pallikonda
    ARABIAN JOURNAL OF GEOSCIENCES, 2020, 13 (02)
  • [7] Neural Network-Based Noise Suppression Algorithm for Star Images Captured During Daylight Hours
    Liu Yuchen
    Zhao Chunhui
    Xu Qing
    ACTA OPTICA SINICA, 2019, 39 (06)
  • [8] Automatic Noise Identification in Images Using Moments and Neural Network
    Vasuki, P.
    Roomi, S. Mohamed Mansoor
    Bhavana, C.
    Deebikaa, E. Lakshmi
    2012 INTERNATIONAL CONFERENCE ON MACHINE VISION AND IMAGE PROCESSING (MVIP), 2012, : 61 - 64
  • [9] Comparative study of deep neural networks with unsupervised Noise2Noise strategy for noise reduction of optical coherence tomography images
    Qiu, Bin
    Zeng, Shuang
    Meng, Xiangxi
    Jiang, Zhe
    You, Yunfei
    Geng, Mufeng
    Li, Ziyuan
    Hu, Yicheng
    Huang, Zhiyu
    Zhou, Chuanqing
    Ren, Qiushi
    Lu, Yanye
    JOURNAL OF BIOPHOTONICS, 2021, 14 (11)
  • [10] Noise suppression and the method evaluation for ladar range images
    Key Laboratory of Dynamics and Control of Flight Vehicle, School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China
    不详
    Guangdianzi Jiguang, 6 (1215-1221): : 1215 - 1221