NVST Image Denoising Based on Self-Supervised Deep Learning

被引:3
|
作者
Lu Xianwei [1 ]
Liu Hui [2 ]
Shang Zhenhong [1 ,3 ]
机构
[1] Kunming Univ Sci & Technol, Fac Informat Engn & Automat, Kunming 650500, Yunnan, Peoples R China
[2] Chinese Acad Sci, Yunnan Observ, Kunming 650216, Yunnan, Peoples R China
[3] Kunming Univ Sci & Technol, Yunnan Key Lab Artificial Intelligence, Kunming 650500, Yunnan, Peoples R China
关键词
image processing; image denoising; new vacuum solar telescope images; self-supervised learning; correlation analysis; power spectrum analysis;
D O I
10.3788/LOP202158.0610018
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
As one of the most important optical solar telescopes for studying solar physics, the new vacuum solar telescope (NVST) suffers from various noise interferences in the process of collecting image data, which affects the study of observation data. Some methods based on standard supervised deep learning have achieved remarkable results in the field of image denoising. However, this type of method becomes inapplicable to the field of astronomical images where clean data is difficult to obtain. To solve this problem, this paper applies the image denoising method based on self-supervised deep learning to NVST image denoising. In order to quantitatively evaluate the performance of the network model, first, add simulation noise to the reconstructed data; second, the noisy data is estimated through the noise level estimation network to estimate the noise level; then, self-supervised convolution blind spot network is used to learn image features, and the image is restored by Baycsian inference; finally, the experimental results arc quantitatively analyzed through the peak signal-to-noise ratio (PSNR) and structural similarity evaluation indicators, correlation analysis, and power spectrum analysis. Experimental results show that, whether for simulated noise data or actual observation data, compared with other image denoising methods in the experiment, the proposed method can effectively reduce the interference of noise on NVST images and improve the image PSNR. At the same time, it also provides solutions for other engineering fields where clean image data is difficult to obtain.
引用
收藏
页数:12
相关论文
共 29 条
  • [1] Deep learning
    LeCun, Yann
    Bengio, Yoshua
    Hinton, Geoffrey
    [J]. NATURE, 2015, 521 (7553) : 436 - 444
  • [2] Stokes inversion based on convolutional neural networks
    Asensio Ramos, A.
    Baso, C. J. Diaz
    [J]. ASTRONOMY & ASTROPHYSICS, 2019, 626
  • [3] Birney DS, 2006, OBSERVATIONAL ASTRONOMY, 2ND EDITION, P1
  • [4] Bromiley P A, EB OL
  • [5] ChaeJ J, 2008, ASTROPHYSICAL J, V548, P497
  • [6] Image denoising by sparse 3-D transform-domain collaborative filtering
    Dabov, Kostadin
    Foi, Alessandro
    Katkovnik, Vladimir
    Egiazarian, Karen
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (08) : 2080 - 2095
  • [7] Noise-gating to Clean Astrophysical Image Data
    DeForest, C. E.
    [J]. ASTROPHYSICAL JOURNAL, 2017, 838 (02):
  • [8] Model-blind Video Denoising Via Frame-to-frame Training
    Ehret, Thibaud
    Davy, Axel
    Morel, Jean-Michel
    Facciolo, Gabriele
    Arias, Pablo
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 11361 - 11370
  • [9] Toward Convolutional Blind Denoising of Real Photographs
    Guo, Shi
    Yan, Zifei
    Zhang, Kai
    Zuo, Wangmeng
    Zhang, Lei
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 1712 - 1722
  • [10] He W J, 2011, WUHAN HUAZHONG U SCI, P5