GLADUnet: global-local attention and dynamic upsampling for ancient manuscript denoising and binarization
Source abstract
Abstract
Ancient manuscripts require digitization to combat deterioration and enable preservation. This study addresses challenges in multilingual document processing, including noise, texture variations, and ink fading, by proposing GLADUnet – a Global-Local Attention Dynamic UNet for denoising and binarization. The method employs convolutional neural networks (CNNs) with Spatial Group-wise Enhancement to extract character features, integrates a global-local attention module for noise reduction, and utilizes a UNet decoder with dynamic upsampling for precise image reconstruction. We construct a multilingual dataset covering 12 scripts to evaluate the framework. The experimental results demonstrate that GLADUnet shows excellent performance and can effectively handle the noise reduction and binarization tasks of multilingual ancient book document images. The model’s cross-dataset validation confirms its robustness for historical document processing tasks. This approach significantly improves optical character recognition (OCR) accuracy by effectively separating text from complex backgrounds and noise.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Handwritten Text Recognition Techniques · Image Processing and 3D Reconstruction · Generative Adversarial Networks and Image Synthesis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (35)
Show source-provided references
1. Wenjun, Z., Benpeng, S., Ruiqi, F., Xihua, P. & Shanxiong, C. Ea-gan: restoration of text in ancient chinese books based on an example attention generative adversarial network. Heritage Sci. 11, 42 (2023).10.1186/s40494-023-00882-y ↗
2. Gao, Z. et al. Application of hyperspectral imaging technology to digitally protect murals in the Qutan Temple. Heritage Sci. 11, 8 (2023).10.1186/s40494-022-00847-7 ↗
3. Farhat, A. et al. Optical character recognition on heterogeneous soc for hd automatic number plate recognition system. EURASIP J. Image Video Process. 2018, 1–17 (2018).10.1186/s13640-018-0298-2 ↗
4. Mustafa, W. A. & Kader, M. M. M. A. Binarization of document images: a comprehensive review. J. Phys. Conf. Ser. 1019, 012023 (2018).10.1088/1742-6596/1019/1/012023 ↗
5. Lombardi, F. & Marinai, S. Deep learning for historical document analysis and recognition-a survey. J.Imag. 6, 110 (2020).10.3390/jimaging6100110 ↗
6. Van der Walt, S. et al. scikit-image: image processing in Python. PeerJ 2, e453 (2014).10.7717/peerj.453 ↗
7. Otsu, N. et al. A threshold selection method from gray-level histograms. Automatica 11, 23–27 (1975).
8. Niblack, W. An Introduction To Digital Image Processing Vol. 162 (Strandberg Publishing Company, DNK, 1985).
9. Sauvola, J. & Pietikäinen, M. Adaptive document image binarization. Pattern Recogn. 33, 225–236 (2000).10.1016/S0031-3203(99)00055-2 ↗
10. Pandey, S. & Bharti, J. Document enhancement and binarization using deep learning approach. In Proceedings of Third International Conference on Intelligent Computing, Information and Control Systems: ICICCS 2021, 133–145 (Springer, 2022).10.1007/978-981-16-7330-6_11 ↗
11. Calvo-Zaragoza, J. & Gallego, A.-J. A selectional auto-encoder approach for document image binarization. Pattern Recogn. 86, 37–47 (2019).10.1016/j.patcog.2018.08.011 ↗
12. Li, D., Wu, Y. & Zhou, Y. Sauvolanet: learning adaptive sauvola network for degraded document binarization. In International Conference on Document Analysis and Recognition, 538–553 (Springer, 2021).10.1007/978-3-030-86337-1_36 ↗
13. He, S. & Schomaker, L. Deepotsu: Document enhancement and binarization using iterative deep learning. Pattern Recogn. 91, 379–390 (2019).10.1016/j.patcog.2019.01.025 ↗
14. Xiong, W. et al. Dp-linknet: A convolutional network for historical document image binarization. KSII Trans. Int. Inform. Syst. ((TIIS)) 15, 1778–1797 (2021).
15. Souibgui, M. A. & Kessentini, Y. De-gan: A conditional generative adversarial network for document enhancement. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1180–1191 (2020).10.1109/TPAMI.2020.3022406 ↗
16. Bezmaternykh, P. V., Ilin, D. A. & Nikolaev, D. P. U-net-bin: hacking the document image binarization contest. Кмпьютерная Oптика 43, 825–832 (2019).
17. Tensmeyer, C. & Martinez, T. Document image binarization with fully convolutional neural networks. In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 99–104 (IEEE, 2017).10.1109/ICDAR.2017.25 ↗
18. Pan, S. J. & Yang, Q. A survey on transfer learning. IEEE Trans. knowl. Data Eng. 22, 1345–1359 (2009).10.1109/TKDE.2009.191 ↗
19. Bahdanau, D., Cho, K. & Bengio, Y. Neural Machine Translation by Jointly Learning to Align and Translate, 3rd International Conference on Learning Representations (ICLR 2015).
20. Lin, T.-Y. et al. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2117–2125 (IEEE, 2017).10.1109/CVPR.2017.106 ↗
21. Shorten, C. & Khoshgoftaar, T. M. A survey on image data augmentation for deep learning. J. Big Data 6, 1–48 (2019).10.1186/s40537-019-0197-0 ↗
22. Chinese Minority Languages, I., Ancient Books, M. A. B. P., Central University for Nationalities & of the State People’s Committee, I. C. Compilation of Rare Books in Chinese Minority Scripts (Fuzhou: Fujian People’s Publishing House, Chinese, 2017).
23. Organization, P. O. & of Ethnic Minority Ancient Books in Yunnan Province, P. Yunnan Minority Ancient Books (Kunming: Yunnan People’s Publishing House, Chinese, 2014).
24. Shouren, W. Chuanxilu (University of Michigan Press, 2023).
25. Märgner, V. & El Abed, H. Icdar 2009 Arabic Handwriting Recognition Competition. In 2009 10th International Conference on Document Analysis and Recognition, 1383–1387 (IEEE, 2009).10.1109/ICDAR.2009.256 ↗
26. Pratikakis, I., Gatos, B. & Ntirogiannis, K. H-dibco 2010-handwritten document image binarization competition. In 2010 12th International Conference on Frontiers in Handwriting Recognition, 727–732 (IEEE, 2010).10.1109/ICFHR.2010.118 ↗
27. Pratikakis, I., Gatos, B. & Ntirogiannis, K. Icdar 2011 document image binarization contest (dibco 2011). In 2011 International Conference on Document Analysis and Recognition, 1506–1510 (IEEE, 2011).10.1109/ICDAR.2011.299 ↗
28. Pratikakis, I., Gatos, B. & Ntirogiannis, K. Icfhr 2012 competition on handwritten document image binarization (h-dibco 2012). In 2012 International Conference on Frontiers in Handwriting Recognition, 817–822 (IEEE, 2012).10.1109/ICFHR.2012.216 ↗
29. Pratikakis, I., Gatos, B. & Ntirogiannis, K. ICDAR 2013 document image binarization contest (DIBCO 2013). In 2013 12th International Conference on Document Analysis and Recognition, 1471–1476 (IEEE, 2013).10.1109/ICDAR.2013.219 ↗
30. Pratikakis, I., Zagoris, K., Barlas, G. & Gatos, B. Icdar2017 competition on document image binarization (dibco 2017). In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 1395–1403 (IEEE, 2017).10.1109/ICDAR.2017.228 ↗
31. Pratikakis, I., Zagori, K., Kaddas, P. & Gatos, B. ICFHR 2018 competition on handwritten document image binarization (h-dibco 2018). In 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), 489–493 (IEEE, 2018).10.1109/ICFHR-2018.2018.00091 ↗
32. Konstantinos, N., Basilis, G. & Ioannis, P. Icfhr2014 competition on handwritten document image binarization. In Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, 809–813 (IEEE, 2014).10.1109/ICFHR.2014.141 ↗
33. Burie, J.-C. et al. ICFHR 2016 competition on the analysis of handwritten text in images of Balinese palm leaf manuscripts. In 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 596–601 (IEEE, 2016).10.1109/ICFHR.2016.0114 ↗
34. Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, 234–241 (Springer, 2015).10.1007/978-3-319-24574-4_28 ↗
35. Yang, Z. et al. Docdiff: Document enhancement via residual diffusion models. In Proceedings of the 31st ACM International Conference on Multimedia, 2795–2806 (ACM, 2023).10.1145/3581783.3611730 ↗