Abstract
This paper proposes a new super-resolution approach for low-resolution document images based on dual deep transfer learning and GAN Architecture. It is an improvement of an already existing method but constrained by its poor caliber by its low quality on document images. In these images of complex types, it is necessary to preserve the most details and outlines of text and graphic areas. These constraints were the target of our contribution, which aims to improve the ESRGAN method. The proposed approach is called “Bi-ESRGAN”. It is based on the combination of two ESRGAN networks. The networks act in double focal on two different image maps (full image and details on the contour map) with a collaborative decision. Our approach has been tested and compared on our document image dataset that we built from document images presenting different challenges, categories, complexity levels and degradation kinds. The experimental results carried out are encouraging and confirmed the superiority of our approach compared to more than sixteen existing approaches with and without learning.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Huang, S., Tsai, R.Y.: Multiframe image restoration and registration. Adv. Comput. Vis. Image Process. 1(7), 317–339 (1984)
Prajapati, A., Naik, S., Mehta, S.: Evaluation of different image interpolation algorithms. Int. J. Comput. Appl 58(12), 6–12 (2012). https://doi.org/10.5120/9332-3638
Kawa, S., Kawano, M.: An overview. In: Umehara, H., Okazaki, K., Stone, J.H., Kawa, S., Kawano, M. (eds.) IgG4-Related Disease, pp. 3–7. Springer, Tokyo (2014). https://doi.org/10.1007/978-4-431-54228-5_1
Acharya, T., Tsai, P.-S.: Computational foundations of image interpolation algorithms. Ubiquity 2007, 1–17 (2007)
Burger, W., Burge, M.J.: Digital Image Processing: An Algorithmic Introduction Using Java. Springer London, London (2008)
Li, X., Orchard, M.T.: New edge-directed interpolation. IEEE Trans. Image Process. 10(10), 521–1527 (2001)
Su, D., Willis, P.: Image interpolation by pixel‐level data‐dependent triangulation. In: Computer graphics forum. 9600 Garsington Road, Oxford, OX4 2DQ. Blackwell Publishing Ltd., UK, pp. 189–201 (2004)
Jiji, C.V.: Chaudhuri S: Single-frame image super-resolution through contourlet learning. EURASIP J. Adv. Signal Process 11, 737–767 (2006)
Reddy, K.S., Reddy, K.R.L.: Enlargement of Image Based Upon Interpolation Techniques, Department of Electronics and Communication Engineering VITS, Karimna- gar India (2013)
Sun, J., Zheng, N.N., Tao, H., Shum, H.Y.: Image hallucination with primal sketch priors. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 729–736 (2003)
Ajit, K., Khobragade, S., Nalbalwar, S.: Review of image reconstruction by interpolation techniques. Int. J. Eng. Res. Technol 03, 198–202 (2014)
Roth, S., Black M.J.: Fields of experts: a framework for learning image priors. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, USA (2005)
Anbarjafari, G., Demirel, H.: Image super resolution based on interpolation of wavelet domain high frequency subbands and the spatial domain input image. ETRI J. 32(3), 390–394 (2010)
Jianjun, Z., Cui, Z., Donghao, F., Jinghong, Z.: A new method for super resolution image reconstruction based on surveying adjustment. J. Nanomaterials 2014, 931616 (2014)
Ogawa, Y., Ariki Y., Takiguchi T.: Super-resolution by GMM based conversion using self-reduction image. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Japan, pp. 1285–1288 (2012)
Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision – ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV, pp. 184–199. Springer International Publishing, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_13
Fazli, S., Tahmasebi, M.: PSO and GA based neighbor embedding super resolution. Int. J. Tech. Phys. Problems Eng. 6, 17–21 (2014)
Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1874–1883 (2016)
Kim, J., Lee, K.J., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1646–1654 (2016)
Qin, J., Sun, X., Yan, Y., Jin, L., Peng, X.: Multi-resolution space-attended residual dense network for single image super-resolution. IEEE Access 8, 40499–40511 (2020)
Yu, J., et al.: Wide activation for efficient and accurate image super-resolution (2018)
Chan, K.C.K., Wang, X., Xu, X., Gu, J., Loy, C.C.: Glean: Generative latent bank for large-factor image super-resolution. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 14245–14254 (2021)
Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: 36th International Conference on Machine Learning, ICML, pp. 12744–12753 (2019)
Kezzoula, Z., Faouci, S., Gaceb, Dj.: Neural approach for the magnification of low-resolution document images. In: IEEE, International Conference, AICCSA, pp. 1–8 (2018)
Getreuer, P.: Contour stencils for edge- adaptive image interpolation, vol. 7257. University of California Los Angeles, Mathematics Department, U.S.A (2009)
Akiyama, D., Goto, T.: Improving image quality using noise removal based on learning method for surveillance camera images. In: 2022 IEEE 4th Global Conference on Life Sciences and Technologies (LifeTech), pp. 325–326 (2022)
Wang, X., et al.: Esrgan: Enhanced super-resolution generative adversarial networks. In: Leal-Taixé, L., Roth, S. (eds.) Computer Vision – ECCV 2018 Workshops: Munich, Germany, September 8–14, 2018, Proceedings, Part V, pp. 63–79. Springer International Publishing, Cham (2019). https://doi.org/10.1007/978-3-030-11021-5_5
Nah, S., Kim, T.H., Lee, K.M.: Deep multi-scale convolutional neural network for dynamic scene deblurring. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3883–3891 (2017)
Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impactof residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2016)
Zhu, F.: A review of deep learning based image super-resolution techniques. Comput. Vis. Pattern Recogn. 14, 5423 (2022)
Blau, Y., Mechrez, R., Timofte, R., Michaeli, T., Zelnik-Manor, L.: The 2018 PIRM challenge on perceptual image super-resolution. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops https://doi.org/10.48550/arXiv.1809.07517 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kezzoula, Z., Gaceb, D., Akli, Z., Kahouli, A., Titoun, A., Touazi, F. (2023). Bi-ESRGAN: A New Approach of Document Image Super-Resolution Based on Dual Deep Transfer Learning. In: Salem, M., Merelo, J.J., Siarry, P., Bachir Bouiadjra, R., Debakla, M., Debbat, F. (eds) Artificial Intelligence: Theories and Applications. ICAITA 2022. Communications in Computer and Information Science, vol 1769. Springer, Cham. https://doi.org/10.1007/978-3-031-28540-0_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-28540-0_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-28539-4
Online ISBN: 978-3-031-28540-0
eBook Packages: Computer ScienceComputer Science (R0)