Verification of a static (off-line) signature using a convolutional neural network
https://doi.org/10.21122/2309-4923-2022-1-12-18
Abstract
This article is devoted to the development of a method for detecting forgery of handwritten signatures. The signature still remains one of the most common methods of identification. The signature on financial and other documents can be forged, so detecting forgery is an urgent task. This is the task of binary classification: to determine whether the signature is genuine or fake.
The article describes the results of recognition of handwritten signatures made on paper. A database of handwritten signatures of 10 people was used for experiments. For each person, 10 genuine and 10 forgery signatures made by other people were collected. The signatures were digitized as color images with a resolution of 850×550 pixels. Then a binary representation of each signature was formed. Three variants of reducing signatures to sizes were used for classification: 128×128, 256×256 and 512×512 pixels. These images served as the source data for the convolutional neural network.
As a result of testing the proposed approach, the average accuracy of the correct classification was achieved on medium-sized images and is equal to 93.33%.
About the Authors
U. Yu. Akhundjanov
United Institute of Informatics Problems, National Academy of Sciences of Belarus
Belarus
Akhundjanov Umidjon Yunus ugli, PhD student
Belarus
Akhundjanov Umidjon Yunus ugli, PhD student
V. V. Starovoitov
United Institute of Informatics Problems, National Academy of Sciences of Belarus
Belarus
Starovoitov Valery, Doctor of Sciences and professor of computer science. He is a Principal research fellow
Belarus
Starovoitov Valery, Doctor of Sciences and professor of computer science. He is a Principal research fellow
References
1. Golub Yu., Starovoitov V.V. Image processing of the iris for recognition systems. Minsk: LAPA LAMBERT Academic Publishing House, 2018. 188 p.
2. Bobovkin M.V. Actual problems of the theory and practice of forensic handwriting analysis of the signature // Bulletin of the Moscow University of the Ministry of Internal Affairs of Russia. 2017. No. 2. – P.109-115.
3. Hafemann, L.G. Offline handwritten signature verification — Literature review / L.G. Hafemann, R. Sabourin, L.S. Oliveira // Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA) – 2017. 8p. DOI:10.1109/ipta.2017.8310112.
4. Hadeel J.Jriash. Offline handwritten signature verification system using neural network / J.Jriash Hadeel, A. Z. Abdullah Nada // International Journal of Computer Science and Mobile Computing. – 2015. Vol.4, Issue.10.– P. 403-412.
5. Impedovo S. Verification of Handwritten Signatures: an Overview / S. Impedovo, G. Pirlo // 14th International Conference on Image Analysis and Processing. – 2007. – P.191-196. DOI:10.1109/iciap.2007.4362778.
6. Foroozandeh, A. Offline Handwritten Signature Verification and Recognition Based on Deep Transfer Learning / A. Foroozandeh, A.H. Ataollah, H. Rabbani // International Conference on Machine Vision and Image Processing. – 2020, 7p. DOI: 10.1109/mvip49855.2020.918748.
7. Choi S.S. A survey of binary similarity and distance measures / S. S. Choi, S. H. Cha, C.C. Tappert // Journal of Systemics, Cybernetics and Informatics. – 2010. – Vol. 8. – No.1. – P. 43–48.
8. Canbek G. Binary classification performance measures/metrics: A comprehensive visualized roadmap to gain new insights / G. Canbek, S. Sagiroglu, T.T. Temizel, N. Baykal // International Conference on Computer Science and Engineering. − 2017. – P. 821-826. DOI:10.1109/UBMK.2017.8093539.
9. Sokolova M. Lapalme G. A systematic analysis of performance measures for classification tasks / M. Sokolova // Information Processing & Management. – 2009. – Vol. 45. -№ 4. – P. 427–437.
10. Starovoitov V. V., Golub Y. I. Comparative study of quality estimation of binary classification. Informatics. – 2020. – Vol. 17, no. 1, P. 87−101 (in Russian).
11. Israfilov, Kh.S. Research of image binarization methods / Kh.S. Israfilov // Bulletin of science and education. 2017. No. 6(30). −P. 43–50.
12. Yankovsky, A.A. Criteria for choosing the binarization method for processing images of laboratory analyses. Automated control systems and automation devices URL: https://cyberleninka.ru/article/n/kriterii-vyborametoda-binarizatsii-pri-obrabotke-izobrazheniy-laboratornyh-analizov/viewer.
Review
For citations:
Akhundjanov U.Yu., Starovoitov V.V. Verification of a static (off-line) signature using a convolutional neural network. «System analysis and applied information science». 2022;(1):12-18. (In Russ.) https://doi.org/10.21122/2309-4923-2022-1-12-18
Views:
1571
Email this article 