Optics and Precision Engineering, Volume. 29, Issue 10, 2481(2021)
Fine restoration of incomplete image with external features and image features
Figures & Tables(10)
Fig. 1. Restoration results of the proposed restoration model in this paper
Fig. 2. Schematic diagram of the proposed repair model in this paper
Fig. 4. Network model of the proposed method for fine restoration of incomplete images
Fig. 6. Comparison of the existing restoration model and the restoration model in this paper in the Place2 database， from right to left， the input images， SH， GLCI， CSA， roughly repaired image， EFIF， and the original image
Fig. 7. Comparison of the existing restoration model and the restoration model in this paper in the RUIE database， from right to left， the input images， SH， GLCI， CSA， roughly repaired image， EFIF， and the original image
Fig. 8. Comparison of the existing restoration model and the restoration model in this paper in the Underwater Target database， from right to left， the input images， SH， GLCI， CSA， roughly repaired image， EFIF， and the original image
Fig. 9. Histograms of PSNR and SSIM values for restoration results from this restoration model and comparative restoration models in the Underwater Targe dataset.
Table 1. Objective data for restoration results in Place2， RUIE and Underwater Target database
View tableView in ArticleTable 1. Objective data for restoration results in Place2， RUIE and Underwater Target database
数据集 掩码率 PSNR SSIM SH GLCI CSA 粗修复 EFIF SH GLCL CSA 粗修复 EFIF SH GLCI CSA EFIF Place2 10%-20% 31.34 31.27 33.36 31.03 34.87 0.906 0.911 0.989 0.905 0.987 1.02 1.00 0.78 0.71 20%-30% 30.24 31.79 32.85 30.08 33.12 0.893 0.897 0.982 0.894 0.983 1.57 1.31 0.98 0.94 30%-40% 21.96 24.17 25.16 21.35 24.51 0.886 0.891 0.926 0.887 0.931 2.74 2.36 1.29 1.23 40%-50% 20.39 22.18 24.51 20.40 24.84 0.832 0.853 0.873 0.829 0.894 3.67 3.24 2.85 2.46 RUIE 10%-20% 31.45 33.72 35.84 31.53 35.98 0.929 0.936 0.953 0.925 0.978 1.55 1.47 1.18 1.06 20%-30% 30.75 33.46 34.97 28.95 35.73 0.919 0.925 0.942 0.917 0.971 1.94 1.73 1.56 1.47 30%-40% 27.84 27.76 28.06 27.46 30.93 0.897 0.902 0.916 0.898 0.923 2.95 2.86 2.72 2.55 40%-50% 21.97 23.19 23.97 21.99 24.45 0.846 0.874 0.899 0.841 0.905 3.77 3.78 3.24 3.16 Underwater Target 10%-20% 24.83 25.01 25.42 24.67 27.01 0.913 0.928 0.936 0.915 0.949 1.65 1.44 1.11 1.09 20%-30% 24.36 24.72 25.31 24.21 26.75 0.904 0.916 0.929 0.899 0.935 2.04 1.96 1.54 1.44 30%-40% 20.48 21.14 22.07 20.83 22.35 0.884 0.890 0.907 0.881 0.916 3.27 2.98 2.73 2.49 40%-50% 15.39 15.04 16.42 15.46 16.91 0.862 0.876 0.890 0.868 0.891 4.41 4.04 3.27 3.03
Tools
Get Citation
Copy Citation Text
Tao XU, Ji-yong ZHOU, Guo-liang ZHANG, Lei CAI. Fine restoration of incomplete image with external features and image features[J]. Optics and Precision Engineering, 2021, 29(10): 2481
Paper Information
Category: Information Sciences
Received: Mar. 25, 2021
Accepted: --
Published Online: Nov. 23, 2021
The Author Email: XU Tao (xutao@hist.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20