• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2022, Volume: 15, Issue: 6, Pages: 227-236

Original Article

Identification of Proper and Improper Signatures Using Graph Theory Techniques

Received Date:11 October 2021, Accepted Date:20 January 2022, Published Date:16 February 2022


Objectives: To propose an automatic signature identification for off-line signature utilising graph theory approaches. Methods: Scanned signatures (Kaggle, https://www.kaggle.com/divyanshrai/handwritten-signatures/data) are collected for off-line signature data. The method follows pre-processing, vertex point extraction by midpoint traverse method, features extraction using edge, average edge and average edge D-distance and Support Vector Machine (SVM) to classify and predict the true label for the genuine and forged signatures. False Acceptance Ratio (FAR) and False Rejection Ratio (FRR) give the accuracy of the proposed methods. This off-line signature verification method is compared with the deep learning techniques existing in the literature. Findings: Support Vector Machine (SVM) used for classification and results on standard signature datasets like ICDAR (International Conference on Document Analysis and Recognition). The results demonstrate how the proposed strategy outperforms the state-of-the-art already available. Novelty: The proposed approach use the edge distance, average edge distance, and average edge D-distance inbuilt graph structures to extract the feature points.

Keywords: Signature images; grid approach; bipartite graph; complete bipartite graph; mid point traverse method


  1. Diaz M, Ferrer MA, Impedovo D, Malik MI, Pirlo G, Plamondon R. A Perspective Analysis of Handwritten Signature Technology. ACM Computing Surveys. 2019;51(6):1–39. Available from: https://dx.doi.org/10.1145/3274658
  2. Jagtap AB, Sawat DD, Hegadi RS, Hegadi RS. Verification of genuine and forged offline signatures using Siamese Neural Network (SNN) Multimedia Tools and Applications. 2020;79(47-48):35109–35123. Available from: https://dx.doi.org/10.1007/s11042-020-08857-y
  3. Lai S, Jin L, Zhu Y, Li Z, Lin L. SynSig2Vec: Forgery-free Learning of Dynamic Signature Representations by Sigma Lognormal-based Synthesis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2021;p. 1. Available from: https://dx.doi.org/10.1109/tpami.2021.3087619
  4. Radhika KS, Gopika S. Online and Offline Signature Verification: A Combined Approach. Procedia Computer Science. 2015;46(46):1593–1600. Available from: https://dx.doi.org/10.1016/j.procs.2015.02.089
  5. Vohra K. Signature Verification Using Support Vector Machine and Convolution Neural Network”. Turkish Journal of Computer and Mathematics Education (TURCOMAT). 2021;12(1):80–89. Available from: file:///C:/Users/User/Downloads/1564-Article%20Text-2912-1-10-20210407%20(1).pdf
  6. Xamxidin N, Mamat M, Kang W, Aysa A, Ubul K. Off Line Handwritten Signature Verification Based on Feature Fusion. 2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML). 2021;p. 260–265.
  7. Zhou Y, Zheng J, Hu H, Wang Y. Handwritten Signature Verification Method Based on Improved Combined Features. Applied Sciences. 2021;11(13):5867. doi: 10.3390/app11135867
  8. Sharif M, Khan MA, Faisal M, Fernandes YM, SL. A framework for off-line signature verification system: best features selection approach. Pattern recognition letter. 2018. Available from: https://doi.org/10.1016/j.patrec.2018.01.021
  9. Maergner P, Howe N, Riesen K, Ingold R, Fischer A. Offline Signature Verification Via Structural Methods: Graph Edit Distance and Inkball Models. 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR). 2018;p. 163–168. doi: 10.1109/ICFHR-2018.2018.00037
  10. Maergner P, Howe NR, Riesen K, Ingold R, Fischer A. Graph-based off-line signature verification. 2019. Available from: https://arxiv.org/pdf/1906.10401.pdf
  11. Bhunia AK, Alaei A, Roy PP. Signature verification approach using fusion of hybrid texture features. Neural Computing and Applications. 2019;31(12):8737–8748. Available from: https://dx.doi.org/10.1007/s00521-019-04220-x
  12. Zois EN, Alexandridis A, Economou G. Writer independent offline signature verification based on asymmetric pixel relations and unrelated training-testing datasets. Expert Systems with Applications. 2019;125:14–32. Available from: https://dx.doi.org/10.1016/j.eswa.2019.01.058
  13. Batool FE, Attique M, Sharif M, Javed K, Nazir M, Abbasi AA, et al. Offline signature verification system: a novel technique of fusion of GLCM and geometric features using SVM. Multimedia Tools and Applications. 2020. Available from: https://dx.doi.org/10.1007/s11042-020-08851-4
  14. Ajij M, Pratihar S, Nayak SR, Hanne T, Roy DS. Off-line signature verification using elementary combinations of directional codes from boundary pixels. Neural Computing and Applications. 2021;(1-8). Available from: https://dx.doi.org/10.1007/s00521-021-05854-6
  15. Pham TA, Le HH, Do NT. Offline handwritten signature verification using local and global features. Annals of Mathematics and Artificial Intelligence. 2015;75(1-2):231–247. Available from: https://dx.doi.org/10.1007/s10472-014-9427-5
  16. Serdouk Y, Nemmour H, Chibani Y. New off-line Handwritten Signature Verification method based on Artificial Immune Recognition System. Expert Systems with Applications. 2016;51:186–194. Available from: https://dx.doi.org/10.1016/j.eswa.2016.01.001
  17. Pal S, Alaei A, Pal U, Blumenstein M. Performance of an off-line signature verification method based on texture features on a large indic-script signature dataset. In2016 12th IAPR workshop on document analysis systems (DAS). 2016;p. 72–77. Available from: https://doi.org/10.1016/j.eswa.2016.01.001
  18. Sharif M, Khan MA, Faisal M, Yasmin M, Fernandes SL. A framework for offline signature verification system: Best features selection approach. Pattern Recognition Letters. 2020;139(39):50–59. Available from: https://dx.doi.org/10.1016/j.patrec.2018.01.021
  19. Babu DR, Varma PLN. Average D-Distance Between Edges of a Graph. Indian Journal of Science and Technology. 2015;8(2):152. Available from: https://dx.doi.org/10.17485/ijst/2015/v8i2/58066
  20. Cortes C, Vapnik V. Support-vector networks. Machine Learning. 1995;20(3):273–297. Available from: https://dx.doi.org/10.1007/bf00994018
  21. Vapnik VN. The Nature of Statistical Learning Theory. New-York. Springer New York. 2000.
  22. Liwicki M, Malik MI, Heuvel CEVD, Chen XI, Berger CD, Stoel R, et al. Signature Verification Competition for Online and Offline Skilled Forgeries (SigComp2011) 2011 International Conference on Document Analysis and Recognition. 2011. Available from: http://www.dfki.de/~liwicki/SigComp2011/trainingSet.zip
  23. Navid SMA, Priya SH, Khandakar NH, Ferdous Z, Haque AB. Signature Verification Using Convolutional Neural Network. 2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON). 2019;p. 35–39.


© 2022 Raj et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.