Image reconstruction of traditional Chinese painting works based on depth learning

被引：0

作者：

Li, Xiyang ^{[1
]}

Ku, Wenzhen ^{[2
]}

机构：

[1] College of Fine Arts and Design, Hunan City University, Hunan, Yiyang

[2] College of Materials and Chemical Engineering, Hunan City University, Hunan, Yiyang

来源：

International Journal of Reasoning-based Intelligent Systems | 2024年 / 16卷 / 04期

关键词：

Chinese painting works; colour component; deep learning; Gaussian filtering; image reconstruction; residual network;

D O I：

10.1504/IJRIS.2024.142352

中图分类号：

学科分类号：

摘要：

Aiming at the problems of large sparse decomposition error of pixel signal, low reconstruction accuracy and slow reconstruction speed in traditional Chinese painting image reconstruction, a method of traditional Chinese painting image reconstruction based on depth learning is proposed. The image signal of traditional Chinese painting works is decomposed sparsely by the dictionary. The traditional Chinese painting image is weighted according to the Gaussian filter, the impurities in the signal are removed by the bilateral filter method, and the edge of the traditional Chinese painting image is corrected by the colour component method. This is to build the depth learning model of the traditional Chinese painting image reconstruction and achieve accurate and efficient reconstruction. The results show that this method can reduce the sparse decomposition error of pixel signal, less than 0.15%, the reconstruction accuracy reaches 97%, and the reconstruction time is shortened, the maximum time is only 1.5 s, indicating that this method is feasible. Copyright © 2024 Inderscience Enterprises Ltd.

引用

页码：267 / 277

页数：10

共 20 条

[1]

Chen H., Qin Y., Feng C., Ren H., Chang L., Fractional-order total variation algorithm with nonlocal self-similarity for image reconstruction, Journal of Electronic Imaging, 30, 1, pp. 625-631, (2021)

[2]

Dai C., Che H., Leung M.F., A neurodynamic optimization approach for L1 minimization with application to compressed image reconstruction, International Journal on Artificial Intelligence Tools, 15, 7, pp. 145-149, (2021)

[3]

Huang J.W., Lv S.X., Zhang Z.S., Yuan H.Q., Chaotic signal denoising algorithm based on sparse decomposition, Chinese Physics B, 29, 6, pp. 1108-1110, (2020)

[4]

Huang S., Hu H., Yang Y., Wan W., Wu Z., Image super resolution reconstruction network based on EM self-attention residual, Journal of Beijing University of Aeronautics and Astronautics, 12, 13, pp. 1-12, (2012)

[5]

Jiang Y., Liu Y., Zhan W., Et al., Lightweight dual-stream residual network for single image super-resolution, IEEE Access, 9, 1, pp. 129890-129901, (2021)

[6]

Kong L., Zhu J., Ying S., Local stereo matching using adaptive cross-region-based guided image filtering with orthogonal weights, Mathematical Problems in Engineering, 11, 2, pp. 1-20, (2021)

[7]

Li H., Fan Y., MDReg‐Net: multi‐resolution diffeomorphic image registration using fully convolutional networks with deep self‐supervision, Human Brain Mapping, 43, 7, pp. 2218-2231, (2022)

[8]

Li H., He X., Yu Z., Luo J., Noise-robust image fusion with low-rank sparse decomposition guided by external patch prior – ScienceDirect, Information Sciences, 523, 24, pp. 14-37, (2020)

[9]

Li Z., Zhang T., Zhang D., MRI image reconstruction based on self-supervised edge fusion network, Pattern Recognition and Artificial Intelligence, 34, 4, pp. 361-366, (2021)

[10]

Maj M., Comparison of machine learning methods for image reconstruction using the LSTM classifier in industrial electrical tomography, Energies, 14, 21, (2021)

← 1 2 →