CNN-BILSTM Architectures for Handwritten Signature Verification: Insights and Innovations

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2025 | Volume : 12 | Issue : 02 | Page : –
    By

    Manmohan Jatav,

  • Shivank Kumar Soni,

  1. Research Scholar, Department of Computer Science and Engineering, Oriental Institute of Science & Technology, Bhopal, Madhya Pradesh, India
  2. Assistant Professor, Department of Computer Science and Engineering, Oriental Institute of Science & Technology, Bhopal, Madhya Pradesh, India

Abstract

document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_abs_186593’);});Edit Abstract & Keyword

Verifying handwritten signatures is essential for identity authentication to guard against fraud and guarantee security across a range of platforms. The approaches and developments in handwritten signature verification are examined in this review paper, with an emphasis on both offline and online techniques. While online methods use dynamic information like stroke or der and speed collected by specialized devices, offline verification uses scanned photographs of signatures. Even if technology is moving toward online approaches more and more, offline systems are still needed, especially in settings where paper is used extensively. The difficulties of offline signature verification are discussed in the study, with a focus on the difficulties of feature extraction in the absence of dynamic data inputs. It also examines the development of handwritten text recognition, emphasizing the function of recurrent and convolutional neural networks, as well as its uses in optical character recognition (OCR). We evaluate and analyze various deep learning methods for handwritten document recognition, including advantages and disadvantages. Offline Handwritten Text Recognition (OHTR) has a comprehensive framework that includes phases for feature extraction, classification, and preprocessing. Lastly, a review of current developments and their consequences is given regarding the integration of CNNs and LSTMs in handwriting recognition.

Keywords: Handwritten signature verification, offline signature verification, online signature verification, convolutional neural networks (CNNs), recurrent neural networks (RNNs), optical character recognition (OCR)

[This article belongs to Journal of Image Processing & Pattern Recognition Progress ]

How to cite this article:
Manmohan Jatav, Shivank Kumar Soni. CNN-BILSTM Architectures for Handwritten Signature Verification: Insights and Innovations. Journal of Image Processing & Pattern Recognition Progress. 2025; 12(02):-.
How to cite this URL:
Manmohan Jatav, Shivank Kumar Soni. CNN-BILSTM Architectures for Handwritten Signature Verification: Insights and Innovations. Journal of Image Processing & Pattern Recognition Progress. 2025; 12(02):-. Available from: https://journals.stmjournals.com/joipprp/article=2025/view=0



document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_ref_186593’);});Edit

References

  1. Akhundjanov U, Soliyev B, Juraev N, Musayev K, Norinov M, Ermatova Z, Zaynabidinov R. Off- line handwritten signature verification based on machine learning. InE3S Web of Conferences 2024 Nov (Vol. 508, p. 03011). EDP Sciences.
  2. Guo Z, Li W, Qian Y, Arandjelovic O, Fang L. A white-box false positive adversarial attack method on contrastive loss based offline handwritten signature verification models. InInternational Conference on Artificial Intelligence and Statistics 2024 Apr 18 (pp. 901-–909). PMLR.
  3. Ozyurt F, Majidpour J, Rashid TA, Koç C. Offline Handwriting Signature Verification: A Transfer Learning and Feature Selection Approach. arXiv preprint arXiv:2401.09467. 2024 Jan 5.
  4. Wang Z, Muhammat M, Yadikar N, Aysa A, Ubul K. Advances in offline handwritten signature recognition research: a review. IEEE Access. 2023 Oct 27;11:120222–36.
  5. Fernandes CP, Montalvo G, Caligiuri M, Pertsinakis M, Guimaraes J. Handwriting changes in Alzheimer’s disease: A systematic review. Journal of Alzheimer’s Disease. 2023 Oct 24;96(1):1-– 1.
  6. Yapıcı MM, Tekerek A, Topaloğlu N. Deep learning-based data augmentation method and signature verification system for offline handwritten signature. Pattern Analysis and Applications. 2021 Feb;24(1):165-–79.
  7. Yapıcı MM, Tekerek A, Topaloğlu N. Deep learning-based data augmentation method and signature verification system for offline handwritten signature. Pattern Analysis and Applications. 2021 Feb;24(1):165-–79.
  8. AlKendi W, Gechter F, Heyberger L, Guyeux C. Advancements and challenges in handwritten text recognition: A comprehensive survey. Journal of Imaging. 2024 Jan 8;10(1):18.
  9. Hassan N, Miah AS, Shin J. A deep bidirectional LSTM model enhanced by transfer-learning-based feature extraction for dynamic human activity recognition. Applied Sciences. 2024 Jan 10;14(2):603.
  10. Riahi M, Eslami M, Safavi SH, Torkamani Azar F. Human activity recognition using improved dynamic image. IET Image Processing. 2020 Nov;14(13):3223-31.
  11. Agrahari S, Tiwari AK. Text Recognition using Deep Learning: A Review. Inpresented at the International Conference on Advanced Computing and Software Engineering, SCITEPRESS 2021 Feb (pp. 106-–114).
  12. Chung J, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555. 2014 Dec 11.
  13. Al-Selwi SM, Hassan MF, Abdulkadir SJ, Muneer A, Sumiea EH, Alqushaibi A, Ragab MG. RNN- LSTM: From applications to modeling techniques and beyond—Systematic review. Journal of King Saud University-Computer and Information Sciences. 2024 May 21:102068.
  14. Malashin I, Tynchenko V, Gantimurov A, Nelyub V, Borodulin A. Applications of Long Short- Term Memory (LSTM) Networks in Polymeric Sciences: A Review. Polymers. 2024 Sep 14;16(18):2607.
  15. Agrawal V, Jagtap J, Kantipudi MP. Exploration of advancements in handwritten document recognition techniques. Intelligent Systems with Applications. 2024 Mar 15:200358.
  16. Wang Y, Xiao W, Li S. Offline handwritten text recognition using deep learning: A review. InJournal of Physics: Conference Series 2021 Apr 1 (Vol. 1848, No. 1, p. 012015). IOP Publishing.
  17. Min F, Zhu S, Wang Y. Offline handwritten Chinese character recognition based on improved GoogLeNet. InProceedings of the 2020 3rd International Conference on Artificial Intelligence and Pattern Recognition 2020 Jun 26 (pp. 42-–46).
  18. Giménez A, Khoury I, Andrés-Ferrer J, Juan A. Handwriting word recognition using windowed Bernoulli HMMs. Pattern Recognition Letters. 2014 Jan 1;35:149–56.
  19. Kothawade D, Kazi I, Mhatre J, Nair K, Nitnaware P. Recognition of labels for hand drawn images. International Research Journal of Engineering and Technology (IRJET). 2020;7(5):1819–23.
  20. EL Mouna L, Silkan H, Hanyf Y, Farouk Nanne M. A Combined Deep Cnn-Lstm Network For Sketch Recognition. International Journal of Computing and Digital Systems. 2024 Aug 1;16(1):633–44.
  21. Jones K, Bird C. Complexity, Features, and Comparisons in Forensic Handwriting Examination. Wiley Interdisciplinary Reviews: Forensic Science. 2025 Mar;7(1):e1537.
  22. Crot S, Marquis R. A comparative review of error rates in forensic handwriting examination. Journal of Forensic Sciences. 2024 Nov;69(6):2127-–38.
Regular Issue Subscription Original Research
Volume 12
Issue 02
Received 04/02/2025
Accepted 07/03/2025
Published 28/04/2025
Publication Time 83 Days
193

[first_name] [last_name]

My IP

PlumX Metrics