Abstract
In this paper, we propose a unified approach for denoising and super-resolution of document images. The approach is a one shot unpaired technique where a single unpaired example is used as reference for training a SinGAN (Shaham et al., in: Proceedings of the IEEE/CVF international conference on computer vision, 2019) model. The training is carried out in 2 steps. First we use a clean reference image to train a SinGAN to learn the characteristics of the clean image. Then we perform super resolution and denoising of given test image using another SinGAN. Our unique formulation of the loss function helps in this task by prompting the generated images to have characteristics similar to the reference clean image. We conduct experiments on publicly available datasets (Kaggle Dirty Documents Images and DIBCO) and obtain promising results. We also evaluate the performance of our model for OCR and obtain a higher recognition rate compared to competing methods.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12046-023-02326-6/MediaObjects/12046_2023_2326_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12046-023-02326-6/MediaObjects/12046_2023_2326_Fig2_HTML.png)
Similar content being viewed by others
References
Likforman-Sulem L, Darbon J and Smith E H B 2011 Enhancement of historical printed document images by combining total variation regularization and non-local means filtering. Image and vision computing 29(5): 351–363
Lu S, Chen B M and Ko C C 2006 A partition approach for the restoration of camera images of planar and curled document. Image and Vision Computing 24(8): 837–848
Mitianoudis N and Papamarkos N 2015 Document image binarization using local features and gaussian mixture modeling. Image and Vision Computing 38: 33–51
Shocher A, Cohen N and Irani M 2018 “Zero-shot” super-resolution using deep internal learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3118–3126
Shaham T R, Dekel T and Michaeli T 2019 Singan: Learning a generative model from a single natural image. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4570–4580
Walha R, Drira F, Lebourgeois F, Alimi A M and Garcia C 2016 Resolution enhancement of textual images: a survey of single image-based methods. IET Image Processing 10(4): 325–337
Buades A, Coll B and Morel J-M 2005 A review of image denoising algorithms, with a new one. Multiscale modeling & simulation 4(2): 490–530
Awad A 2019 Denoising images corrupted with impulse, gaussian, or a mixture of impulse and gaussian noise. Engineering Science and Technology, an International Journal 22(3): 746–753
Ling BW-K, Ho CY-F, Dai Q and Reiss J D 2014 Reduction of quantization noise via periodic code for oversampled input signals and the corresponding optimal code design. Digital Signal Processing 24: 209–222
Rajagopal A, Hamilton R B and Scalzo F 2016 Noise reduction in intracranial pressure signal using causal shape manifolds. Biomedical signal processing and control 28: 19–26
Ilesanmi A E, Idowu O P, Chaumrattanakul U and Makhanov S S 2021 Multiscale hybrid algorithm for pre-processing of ultrasound images. Biomedical Signal Processing and Control 66: 102396
Huang T S 1972 Stability of two-dimensional recursive filters. IEEE Transactions on Audio and Electroacoustics 20: 158–163
Zhao H and Zheng Z 2016 Bias-compensated affine-projection-like algorithms with noisy input. Electronics Letters 52(9): 712–714
Ilesanmi A E and Ilesanmi T O 2021 Methods for image denoising using convolutional neural network: A review. Complex & Intelligent Systems 7(5): 2179–2198
Lucas A, Iliadis M, Molina R and Katsaggelos A K 2018 Using deep neural networks for inverse problems in imaging: beyond analytical methods. IEEE Signal Processing Magazine 35(1): 20–36
Koesten L, Simperl E, Blount T, Kacprzak E and Tennison J 2020 Everything you always wanted to know about a dataset: Studies in data summarisation. International Journal of Human-Computer Studies 135: 102367
**ao-Jiao Mao, Chunhua Shen and Yang B Y 2016 Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Proc. Advances in Neural Information Processing Systems (NIPS)
Zhang K, Zuo W, Chen Y, Meng D and Zhang L 2017 Beyond a Gaussian denoiser: Residual learning of deep cnn for image denoising.IEEE Transactions on Image Processing
Shi W, Jiang F, Zhang S, Wang R, Zhao D and Zhou H 2019 Hierarchical residual learning for image denoising. Signal Processing: Image Communication 76: 243–251
Li X, **ao J, Zhou Y, Yuanzheng Y, Nianzu L, Wang X, Wang S and Gao S 2020 Detail retaining convolutional neural network for image denoising. Journal of Visual Communication and Image Representation, 71
Guo B., Song K., Dong H., Yan Y., Tu Z., and Zhu L. 2020. NERnet: Noise estimation and removal network for image denoising. Journal of Visual Communication and Image Representation, 71
Ronneberger O, Fischer P and Brox T 2015 U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, LNCS 9351: 234–241
Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A and Bengio Y 2020 Generative adversarial networks. Communications of the ACM 63(11): 139–144
Lyu Q, Guo M and Pei Z 2020 DeGAN: Mixed noise removal via generative adversarial networks. Applied Soft Computing 95: 106478
Jiang Q, Chen Y, Wang G and Ji T 2020 A novel deep neural network for noise removal from underwater image. Signal Processing: Image Communication 87: 115921
Kim H-J and Lee D 2020 Image denoising with conditional generative adversarial networks (cgan) in low dose chest images. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 954: 161914
Majumdar A 2018 Blind denoising autoencoder. IEEE transactions on neural networks and learning systems 30(1): 312–317
Langarica S and Núñez F 2023 Contrastive blind denoising autoencoder for real time denoising of industrial iot sensor data. Engineering Applications of Artificial Intelligence 120: 105838
Lehtinen J, Munkberg J, Hasselgren J, Laine S, Karras T, Aittala M and Aila T 2018 Noise2Noise: Learning image restoration without clean data. In: Proc. International Conference on Machine Learning
Pang T, Zheng H, Quan Y and Ji H 2021 Recorrupted-to-recorrupted: unsupervised deep learning for image denoising. In: Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 2043–2052
Krull A, Buchholz T-O and Jug F 2019 Noise2Void-learning denoising from single noisy images. In: Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 2129–2137
Krull A, Vičar T, Prakash M, Lalit M and Jug F 2020 Probabilistic noise2void: Unsupervised content-aware denoising. Frontiers in Computer Science 2: 5
Sharma M, Ray A, Chaudhury S and Lall B 2017 A noise-resilient super-resolution framework to boost ocr performance. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 1: 466–471. IEEE
Xu X, Sun D, Pan J, Zhang Y, Pfister H and Yang M-H 2017 Learning to super-resolve blurry face and text images. In: Proceedings of the IEEE International Conference on Computer Vision, pages 251–260
Salismans T, Goodfellow I, Zaremba W, Cheung V, Radford A and Chen X 2016 Improved techniques for training GANs. In: Advances in Neural Information Processing Systems (NIPS)
Ray A, Sharma M, Upadhyay A, Makwana M, Chaudhury S, Trivedi A, Singh A and Saini A 2019 An end-to-end trainable framework for joint optimization of document enhancement and recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pages 59–64. IEEE
Mao X, Shen C and Yang Y-B 2016 Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Advances in Neural Information Processing Systems (NIPS)
Haris M, Shakhnarovich G and Ukita N 2018 Deep back-projection networks for super-resolution. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 1664–1673
Peng X and Wang C 2020 Building super-resolution image generator for ocr accuracy improvement. In: International Workshop on Document Analysis Systems, pages 145–160. Springer
Wang Z, Simoncelli E and Bovik A 2003 Multiscale structural similarity for image quality assessment. In: Asilomar Conference on Signals, Systems and Computers, pages 1298 – 1402
Mao X, Li Q, **e H, Lau R, Wang Z and Smolley S P 2017 Least squares generative adversarial networks. In: International Conference on Computer Vision
Jolicoeur-Martineau A 2019 The relativistic discriminator: a key element missing from standard GAN. In: International Conference on Learning Represenations (ICLR)
Yamanaka J, Kuwashima S and Kurita T 2017 Fast and accurate image super resolution by deep cnn with skip connection and network in network. In: International Conference on Neural Information Processing (NIPS), pages 217–225
Quan Y, Yang J, Chen Y, Xu Y and Ji H 2020 Collaborative deep learning for super-resolving blurry text images. IEEE Transactions on Computational Imaging 6: 778–790
Johnson J, Alahi A and Fei-Fei L 2016 Perceptual losses for real-time style transfer and super-resolution. In: European conference on Computer Vision (ECCV), pages 694–711. Springer
Arjovsky M, Chintala S and Bottou L 2017 Wassertein generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML)
Adler J and Lunz S 2018 Banach wasserstein GAN.In: Proc. Advances in Neural Information Processing Systems (NeurIPS)
Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V and Courville A. 2017. Improved Training of Wassertein GANs. In Proceedings Neural Information Processing Systems (NeurIPS)
Hradiš M, Kotera J, Zemcık P and Šroubek F 2015 Convolutional neural networks for direct text deblurring. In: Proceedings of British Machine Vision Conference (BMVC), volume 10
Frank A 2010 UCI machine learning repository. Irvine, CA: University of california, school of information and computer science. http://archive.ics.uci.edu/ml
Dua D and Graff C 2017 UCI machine learning repository
Do T-H, Ramos Terrades O and Tabbone S 2019 DSD: document sparse-based denoising algorithm. Pattern Analysis and Applications 22(1): 177–186
Habibunnisha N, Sivamani K, Seetharaman R and Nedumaran D 2019 Reduction of noises from degraded document images using image enhancement techniques.In: 2019 Third International Conference on Inventive Systems and Control (ICISC), pages 522–525. IEEE
Dumpala V, Kurupathi S R, Bukhari S S Dengel A 2019 Removal of historical document degradations using conditional gans. In: Proceedings of International Conference on Pattern Recognition Applications and Methods (ICPRAM), pages 145–154
Souibgui M A and Kessentini Y 2022 DE-GAN: a conditional generative adversarial network for document enhancement. IEEE Transactions on Pattern Analysis and Machine Intelligence. 44(3): 1180–1191
Acknowledgements
Authors would like to thank Dr. Yashaswi Verma for insightful comments on the paper.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Srivastava, D., Harit, G. Simultaneous denoising and super resolution of document images. Sādhanā 49, 35 (2024). https://doi.org/10.1007/s12046-023-02326-6
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12046-023-02326-6