Education, Science, Technology, Innovation and Life
Open Access
Sign In

Zero-RADCE: Zero-Reference Residual Attention Deep Curve Estimation for Low-Light Historical Tibetan Document Image Enhancement

Download as PDF

DOI: 10.23977/vcip.2023.020101 | Downloads: 31 | Views: 969

Author(s)

Qinghua Zhao 1, Weilan Wang 1

Affiliation(s)

1 Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou, China

Corresponding Author

Weilan Wang

ABSTRACT

To improve the reading experience and the performance of subsequent document analysis and recognition algorithms, the background of low-light document image is expected to be smoothed and its foreground text information needs to be highlighted. The enhanced document images can improve the reading experience and the subsequent document analysis and recognition algorithms. In this paper, first construct a low-light historical Tibetan document image dataset. then improve the deep curve estimation network of Zero-DCE by using encoder-decoder architecture, residual network, and spatial attention mechanism; finally extract the text information features in low-light historical Tibetan document images by specially designed Gaussian and Laplace filters for improving the spatial consistency loss, which not only achieves low-light image enhancement but also improves the spatial consistency loss. Experiments show that the proposed method achieves better results in both quality and quantitative evaluations for low-light historical Tibetan document image enhancement. Meanwhile, the training parameters are reduced by 39.52% and the Flops are reduced by 70.63% compared to the original network.

KEYWORDS

Low-light enhancement, historical tibetan document image, zero-DCE

CITE THIS PAPER

Qinghua Zhao, Weilan Wang, Zero-RADCE: Zero-Reference Residual Attention Deep Curve Estimation for Low-Light Historical Tibetan Document Image Enhancement. Visual Communications and Image Processing (2023) Vol. 2: 1-8. DOI: http://dx.doi.org/10.23977/vcip.2023.020101.

REFERENCES

[1] De, S., Geng, G. Y. X.: Research on the sharing model of Tibetan literature resources under the network environment. Tibetan Studies in China 02, 202-206(2013).
[2] Guo, C., Li, C., J, Guo, et al.: Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1780-1789. (2020).
[3] Wei, Chen, et al.: Deep retinex decomposition for low-light enhancement. arXiv preprint arXiv:1808.04560. (2018).
[4] Zhang, Y., Zhang, J., Guo, X: Kindling the darkness: A practical low-light image enhancer. In: Proceedings of the 27th ACM international conference on multimedia, pp. 1632-1640. (2019).
[5] Liu, R., Ma, L., Zhang, J., Fan, X., Luo, Z.: Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10561-10570. (2021).
[6] Wang, Z., Bovik, A. C., Sheikh, H. R., Simoncelli, E. P.: Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13(4), 600-612. (2004).
[7] Pizer, S. M., Amburn, E. P., Austin, J. D., et al.: Adaptive histogram equalization and its variations. Computer vision, graphics, and image processing 39(3), 355-368. (1987).
[8] Farid, H.: Blind inverse gamma correction. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society 10(10), 1428. (2001).
[9] Land, E. H.: The Retinex Theory of Color Vision. Scientific american 237(6), 108-129. (1977).
[10] Ronneberger, O., Fischer, P., Brox, T: U-Net: Convolutional Networks for Biomedical Image Segmentation. In: International Conference on Medical image computing and computer-assisted intervention, pp. 234-241. Springer, Cham (2015).
[11] He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 770-778 (2020).
[12] Woo, S., Park, J., Lee, J. Y., Kweon, I. S.: Cbam: Convolutional block attention module. In: Proceedings of the European conference on computer vision, pp. 3-19. (2018).
[13] Akagic, A., Buza, E., Omanovic, S., Karabegovic, A.: Pavement crack detection using Otsu thresholding for image segmentation. In: 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics, pp. 1092-1097. (2018).

Downloads: 52
Visits: 2881

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.