[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content

Advertisement

Log in

Strike off removal in Indic scripts with transfer learning

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Strike-off text poses major challenges in handwritten text recognition as it changes the semantic and structural information of the image. Although significant results have been achieved in identifying and removing such strike-off data using deep learning methodologies, most have been done for Roman scripts only. Deep learning approaches require a large amount of data with a high cost of training for every script individually to derive effective performance. Due to its complex nature and non-availability of sufficient data, research in strike-off removal in Indic scripts is limited. To address this problem, we propose reducing the requirement of a huge amount of data and minimizing the training cost through transfer learning. With the objective of strike-off removal in multiple Indic scripts, we leverage the experiences of a pre-trained model (trained on the Roman script) for strike-off removal in different domains (Indic scripts). We consider handwritten text documents of \({\textbf {10}}\) different Indic scripts and introduce \({\textbf {7}}\) different strike-offs in these documents. We implement Few-Shot Learning (FSL) and Zero-Shot Learning (ZSL) to train various state-of-the-art deep generative models on a few samples of the mentioned Indic texts. An extensive analysis of the results for ZSL and FSL has been presented with the perspective of source hypothesis generalization capability and the strength of relatedness of source and target domains. The results show that the degree of adaptability of the source hypothesis is significant for the right amount of transfer to take place. The scripts with angular structure have performed better than the round structured scripts as there is a higher degree of relatedness of angular scripts with the Roman script (source script). FSL and ZSL approaches promise to reduce data requirements and training costs for strike-off removal.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

Data set and materials will be made available on request.

Code availability

Code will be made available on request.

References

  1. Adak C, Chaudhuri BB (2014) An approach of strike-through text identification from handwritten documents. In: 2014 14th International Conference on Frontiers in Handwriting Recognition, IEEE, pp 643–648

  2. Alvi AM, Siuly S, Wang H et al (2022) A deep learning based framework for diagnosis of mild cognitive impairment. Knowl Based Syst 248(108):815

    Google Scholar 

  3. Arlandis J, Pérez-Cortes JC, Cano J (2002) Rejection strategies and confidence measures for a k-nn classifier in an ocr task. In: Object recognition supported by user interaction for service robots, IEEE, pp 576–579

  4. Atasever S, Azgınoglu N, Terzı DS et al (2022) A comprehensive survey of deep learning research on medical image analysis with focus on transfer learning. Clin Imaging 94:18–41

    Article  Google Scholar 

  5. Banerjee J, Namboodiri AM, Jawahar C (2009) Contextual restoration of severely degraded document images. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 517–524

  6. Bhattacharya U, Chaudhuri B (2005) Databases for research on recognition of handwritten characters of indian scripts. In: Eighth International Conference on Document Analysis and Recognition (ICDAR’05), IEEE, pp 789–793

  7. Brink A, van der Klauw H, Schomaker L (2008) Automatic removal of crossed-out handwritten text and the effect on writer verification and identification. In: Document Recognition and Retrieval XV, International Society for Optics and Photonics, p 68150A

  8. Eltay M, Zidouri A, Ahmad I et al (2022) Generative adversarial network based adaptive data augmentation for handwritten arabic text recognition. Peer J Comput Sci 8:e861

    Article  Google Scholar 

  9. Fogel S, Averbuch-Elor H, Cohen S, et al (2020) Scrabblegan: Semi-supervised varying length handwritten text generation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4324–4333

  10. Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: International conference on machine learning, PMLR, pp 1180–1189

  11. Gongidi S, Jawahar C (2021) iiit-indic-hw-words: A dataset for indic handwritten text recognition. In: International Conference on Document Analysis and Recognition, Springer, pp 444–459

  12. Goodfellow I, Pouget-Abadie J, Mirza M, et al (2014) Generative adversarial nets. Advances in neural information processing systems. 27

  13. Heil R, Vats E, Hast A (2021) Strikethrough removal from handwritten words using cyclegans. In: International Conference on Document Analysis and Recognition, Springer, pp 572–586

  14. Heil R, Vats E, Hast A (2022) Paired image to image translation for strikethrough removal from handwritten words. arXiv preprint arXiv:2201.09633

  15. Huang JT, Li J, Yu D, et al (2013) Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, pp 7304–7308

  16. Kubicek J, Penhaker M, Krejcar O et al (2021) Modern trends and applications of intelligent methods in biomedical signal and image processing. Sensors 21(3):847

    Article  Google Scholar 

  17. Liao M, Shi B, Bai X, et al (2017) Textboxes: A fast text detector with a single deep neural network. In: Thirty-First AAAI Conference on Artificial Intelligence

  18. Long M, Cao Y, Wang J, et al (2015) Learning transferable features with deep adaptation networks. In: International conference on machine learning, PMLR, pp 97–105

  19. Long M, Zhu H, Wang J, et al (2017) Deep transfer learning with joint adaptation networks. In: International conference on machine learning, PMLR, pp 2208–2217

  20. Luo Z, Zou Y, Hoffman J, et al (2017) Label efficient learning of transferable representations acrosss domains and tasks. Advances in neural information processing systems. 30

  21. Marti UV, Bunke H (2002) The iam-database: an english sentence database for offline handwriting recognition. Int J Doc Anal Recognit 5(1):39–46

    Article  MATH  Google Scholar 

  22. Nicolas S, Paquet T, Heutte L (2006) Markov random field models to extract the layout of complex handwritten documents. In: Tenth International Workshop on Frontiers in Handwriting Recognition, Suvisoft

  23. Nigam S, Behera A, Verma S, et al (2022) Deformity removal from handwritten text documents using variable cycle gan. PREPRINT (Version 1) available at Research Square pp 1–16. https://doi.org/10.21203/rs.3.rs-1488498/v1

  24. Nisa H, Thom JA, Ciesielski V, et al (2019) A deep learning approach to handwritten text recognition in the presence of struck-out text. In: 2019 International Conference on Image and Vision Computing New Zealand (IVCNZ), IEEE, pp 1–6

  25. Niu S, Liu Y, Wang J et al (2020) A decade survey of transfer learning (2010–2020). IEEE Trans Artif Intell 1(2):151–166

    Article  Google Scholar 

  26. Oquab M, Bottou L, Laptev I, et al (2014) Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1717–1724

  27. Pardoe D, Stone P (2010) Boosting for regression transfer. In: ICML

  28. Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621

  29. Pillalamarri A (2018) Evolution of script in india. https://journalsofindia.com/evolution-of-script-in-india/

  30. Pillalamarri A (2019) The story of india’s many scripts. https://thediplomat.com/2019/07/the-story-of-indias-many-scripts/

  31. Poddar A, Chakraborty A, Mukhopadhyay J, et al (2021a) Detection and localisation of struck-out-strokes in handwritten manuscripts. In: International Conference on Document Analysis and Recognition, Springer, pp 98–112

  32. Poddar A, Chakraborty A, Mukhopadhyay J, et al (2021b) Texrgan: a deep adversarial framework for text restoration from deformed handwritten documents. In: Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing, pp 1–9

  33. Rezaei Z, Selamat A, Taki A et al (2017) Automatic plaque segmentation based on hybrid fuzzy clustering and k nearest neighborhood using virtual histology intravascular ultrasound images. Appl Soft Comput 53:380–395

    Article  Google Scholar 

  34. Rosenstein MT (2005) To transfer or not to transfer. In: NIPS 2005

  35. Sarki R, Ahmed K, Wang H et al (2020) Automated detection of mild and multi-class diabetic eye diseases using deep learning. Health Inf Sci Syst 8(1):1–9

    Article  Google Scholar 

  36. Shonenkov A, Karachev D, Novopoltsev M, et al (2021) Handwritten text generation and strikethrough characters augmentation. arXiv preprint arXiv:2112.07395

  37. Sinha RMK (2009) A journey from indian scripts processing to indian language processing. IEEE Ann Hist Comput 31(1):8–31

    Article  MathSciNet  Google Scholar 

  38. Tan C, Sun F, Kong T, et al (2018) A survey on deep transfer learning. In: International conference on artificial neural networks, Springer, pp 270–279

  39. Tzeng E, Hoffman J, Zhang N, et al (2014) Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474

  40. Vizcarra JC, Burlingame EA, Hug CB et al (2022) A community-based approach to image analysis of cells, tissues and tumors. Comput Med Imaging Gr 95(102):013

    Google Scholar 

  41. Wang Y, Yao Q, Kwok JT et al (2020) Generalizing from a few examples: A survey on few-shot learning. ACM Comput Surv (CSUR) 53(3):1–34

    Article  Google Scholar 

  42. Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. J Big data 3(1):1–40

    Article  Google Scholar 

  43. Wigington C, Stewart S, Davis B, et al (2017) Data augmentation for recognition of handwritten words and lines using a cnn-lstm network. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), IEEE, pp 639–645

  44. Xian Y, Lampert CH, Schiele B et al (2018) Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans Pattern Anal Mach Intell 41(9):2251–2265

    Article  Google Scholar 

  45. Xu Y, Pan SJ, Xiong H et al (2017) A unified framework for metric transfer learning. IEEE Trans Knowl Data Eng 29(6):1158–1171

    Article  Google Scholar 

  46. Yao Y, Doretto G (2010) Boosting for transfer learning with multiple sources. In: 2010 IEEE computer society conference on computer vision and pattern recognition, IEEE, pp 1855–1862

  47. Zhu H, Long M, Wang J, et al (2016) Deep hashing network for efficient similarity retrieval. In: Proceedings of the AAAI conference on Artificial Intelligence

  48. Zhu JY, Park T, Isola P, et al (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223–2232

Download references

Author information

Authors and Affiliations

Authors

Contributions

All authors have made equal contribution to the paper.

Corresponding author

Correspondence to Shivangi Nigam.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

Ethics approval

Not Applicable.

Consent to participate

Not Applicable.

Consent for publication

All authors have agreed with the content and give explicit consent to submit the work. All authors have obtained consent from the responsible authorities at the institute/organization where the work has been carried out.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Nigam, S., Behera, A.P., Gogoi, M. et al. Strike off removal in Indic scripts with transfer learning. Neural Comput & Applic 35, 12927–12943 (2023). https://doi.org/10.1007/s00521-023-08433-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-023-08433-z

Keywords

Navigation