Abstract
Signatures are a crucial behavioral trait widely used to authenticate a person's identity. Financial and legal institutions, including commercial banks, consider it a legitimate method of document authentication. Despite the emergence of various biometric authentication techniques such as fingerprints, retinal scans, and facial recognition, signature verification is still a prevalent authentication method among Indian industries, especially in the banking sector. Signature verification is used while processing cheques and other documents, even when only digital copies of such documents are available. An example of signature verification on digital documents is the Cheque Truncation System of India, adopted by all scheduled commercial banks in India. However, manual signature verification is tedious and vulnerable to human error. This paper attempts to compare the efficacy of Convolution Neural Networks and Support Vector Machine algorithms in automating the process of signature verification. These algorithms incorporate various image features to verify whether the signature is genuine or fraudulent without human intervention. The Support Vector Machine algorithm performs better, considering the computational limitations of production systems.
Similar content being viewed by others
Code availability
Codes are available on request.
Data availability
Dutch Data is an open-source, freely available data set.
References
O’Meara G (2019) Mining and classifying images from an advertisement image remover. Ann Data Sci 6:279–303. https://doi.org/10.1007/s40745-018-0164-1
Majeed A (2019) Improving time complexity and accuracy of the machine learning algorithms through selection of highly weighted top k features from complex datasets. Ann Data Sci 6:599–621. https://doi.org/10.1007/s40745-019-00217-4
Saini A, Sharma A (2019) Predicting the unpredictable: an application of machine learning algorithms in Indian stock market. Ann Data Sci. https://doi.org/10.1007/s40745-019-00230-7
Sharma M, Khera SN, Sharma PB (2019) Applicability of machine learning in the measurement of emotional intelligence. Ann Data Sci 6:179–187
Shi Y (2014) Big data: history, current status, and challenges going forward. Bridge 44(4):6–11
Olson DL, Shi Y (2007) Introduction to business data mining. McGraw-Hill/Irwin, New York
Shi Y, Tian YJ, Kou G, Peng Y, Li JP (2011) Optimization based data mining: theory and applications. Springer, London. eBook ISBN 978-0-85729-504-0
Tien JM (2017) Internet of things, real-time decision making, and artificial intelligence. Ann Data Sci 4(2):149–178
Jain AK, Ross AA (2008) Handbook of biometrics. Springer, Boston. Online. ISBN: 978-0-387-71041-9.y
Arathi M, Govardhan A (2014) An efficient offline signature verification system. Int J Mach Learn Comput 4(6):533–537
Eskander GS, Sabourin R, Granger E (2013) Hybrid writer-independent–writer-dependent offline signature verification system. IET Biomet 2:169–181
Edson J, Justino R, Bortolozzi F, Sabourin R (2002) The interpersonal and intrapersonal variability influences on off-line signature verification using HMM. In: Proceedings of the XV Brazilian symposium computer graphics and image processing, pp 197–202
Liwicki M, Malik MI, van den Heuvel CE et al (2011) Signature verification competition for online and offline skilled forgeries (SigComp2011). In: International conference on document analysis and recognition (ICDAR). Beijing, China, pp 1480–1484
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66
Abu-Ain W, Abdullah S, Bataineh B, Abu-Ain T, Omar K (2013) Skeletonization algorithm for binary images. Proced Technol 11:704–709. https://doi.org/10.1016/j.protcy.2013.12.248
Saeed K, Tabędzki M, Rybnik M, Adamski M (2010) K3M: a universal algorithm for image skeletonization and a review of thinning techniques. Int J Appl Math Comput Sci 20(2):317–335. https://doi.org/10.2478/v10006-010-0024-4
Zhang TY, Suen CY (1984) A fast parallel algorithm for thinning digital patterns. Commun ACM 27(3):236–239. https://doi.org/10.1145/357994.358023
Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3(6):610–621
Hossain MRI, Ahmed I, Kabir MH (2015) Automatic lung tumor detection based on GLCM features. In: Jawahar C, Shan S (eds) Computer vision: ACCV 2014 workshops. ACCV 2014. Lecture notes in computer science, vol 9010. Springer, Cham. https://doi.org/10.1007/978-3-319-16634-6_9
Fukushima K (1980) Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 36(4):93–202
LeCun Y, Bengio Y (1995) Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks MA Arbib. MIT Press, Cambridge
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proceed IEEE 86:2278–2324
Wong SC, Gatt A, Stamatescu V, Mcdonnell MD (2016) Understanding data augmentation for classification: when to warp? Int Conf Dig Image Comput Techn Appl (DICTA)
Cortes C, Vapnik V (1995) Support-vector networks. Kluwer Academic Publishers, New York, pp 273–297
Jain S (2013) A machine learning approach: SVM for image classification in CBIR. IAJIEM 2(4):446–452
Thai LH, Hai TS, Thuy NT (2012) Image classification using support vector machine and artificial neural network. IJ Inform Technol Comput Sci 5:32–38
Jabr ZF, Saleh SR, Fasial AN (2016) A hybrid features for signature recognition using neural network. J Thi-Qar Sci 6(1):83–88
Acknowledgements
The authors express their profound gratitude to Mr. Anup Kumar Mahapatra (Deputy Managing Director and Chief Information Officer, Global IT Center, The State Bank of India), Mr. Kunjal Prasad (former General Manager, Data and Analytics, Global IT Center, The State Bank of India), Mr. NDSV Nageswara Rao (Erstwhile Deputy General Manager, Analytics, Global IT Center, The State Bank of India), Mr. Kamal Kishor Naik (Chief Manager, Analytics, Global IT Center, The State Bank of India)), Mr. Komaragiri Srinivas Jagannath (Deputy Manager, Analytics, Global IT Center, The State Bank of India) and Ms. Vatsala Sinha(Intern) for their valuable contributions, feedback, and suggestions. We are also very thankful to all volunteers who provided signatures and helped create the dataset used for model building.
Funding
NA.
Author information
Authors and Affiliations
Contributions
PS proposed the problem, analyzed the data, build the models, and did the initial literature writing. Dr. PV designed the study, reviewed the literature, revised the manuscript critically for important intellectual content, and gave final approval of the version to be published. NS Conceptualized the problem, provided his inputs for model building and performed the relevant statistical analysis, did model validation, and reviewed the literature. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethical statements
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Singh, P., Verma, P. & Singh, N. Offline Signature Verification: An Application of GLCM Features in Machine Learning. Ann. Data. Sci. 9, 1309–1321 (2022). https://doi.org/10.1007/s40745-021-00343-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40745-021-00343-y