Volume: 1 Issue: 1
Year: 2025, Page: 29-36,
Received: May 20, 2025 Accepted: Sept. 20, 2025 Published: Sept. 28, 2025
Offline signature verification is a difficult task in the biometric authentication domain, with particular importance in legal documents, banking activities, and identity management systems. The performance of offline signature verification systems is heavily reliant on the quality of features extracted. Feature extraction forms the cornerstone upon which sophisticated models perceive, analyze, and make sense of digital data. This paper delves into the intricacies of feature extraction, examining its significance and associated challenges. In this paper, three feature extraction methods, namely Histogram of Oriented Gradients (HOG), which captures directional and structural local edges, GLCM (capturing statistical texture information), and Local Binary Pattern (LBP), have been exploited. Instead of using a single classifier, a Voting Classifier is used, which includes Support Vector Machines (SVM), Random Forests (RF), and K-nearest neighbor (KNN) for discriminating genuine and forged signatures. The proposed models are evaluated on five benchmark datasets: CEDAR, BHSig260 (Bengali and Hindi), UTSig, and MCYT-75.
Keywords: Offline Signature Verification, GLCM, HOG, LBP, SVM, Random Forest, K-nearest neighbor, Voting Classifier
[1] Lokare, C., Patil, R., Rane, S., Kathirasen, D., & Mistry, Y. (2021). Offline handwritten signature verification using various Machine Learning Algorithms. In ITM Web of Conferences (Vol. 40, p. 03010). EDP Sciences.
[2] Roy, S., Sarkar, D., Malakar, S., & Sarkar, R. (2023). Offline signature verification system: a graph neural network based approach. Journal of Ambient Intelligence and Humanized Computing, 1-11.
[3] Hashim, Z., Mohsin, H., & Alkhayyat, A. (2024). Signature verification based on proposed fast hyper deep neural network. IAES Int J Artif Intell, 13(1), 961-73.
[4] Alsuhimat, F. M., & Mohamad, F. S. (2023). A hybrid method of feature extraction for signatures verification using CNN and HOG a multi-classification approach. IEEE Access, 11, 21873-21882.
[5] Alsuhimat, F. M., & Mohamad, F. S. (2023). Offline signature verification using long short-term memory and histogram orientation gradient. Bulletin of Electrical Engineering and Informatics, 12(1), 283-292.
[6] Bhavani, S. D., & Bharathi, R. K. (2024). A multi-dimensional review on handwritten signature verification: strengths and gaps. Multimedia Tools and Applications, 83(1), 2853-2894.
[7] Wang, Y., Zheng, J., & Zhou, Y. (2022, September). An Efficient Offline Signature Verification Method Based on Improved Feature Extraction. In 2022 2nd International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) (pp. 609-612). IEEE.
[8] Diaz, M., Ferrer, M. A., Impe dovo, D., Malik, M. I., Pirlo, G., & Plamondon, R. (2019). A perspective analysis of handwritten signature technology. A cm Computing Surveys (C sur), 51(6), 1-39.
[9] Swamy, M. R., Vijayalakshmi, P., & Rajendran, V. (2025, February). Signature verification based on machine learning and deep learning techniques: A review. In AIP Conference Proceedings (Vol. 3162, No. 1). AIP Publishing.
[10] Badie, A., & Sajedi, H. (2024). Offline handwritten signature authentication using Graph Neural Network methods. International Journal of Information Technology, 1-11.
[11] J. Poddar, V. Parikh, and S. K. Bharti, “Offline signature recognition and forgery detection using deep learning,” Procedia Computer Science, vol. 170, pp. 610–617, 2020, doi: 10.1016/j.procs.2020.03.133.
[12] S. Rana, A. Sharma, and K. Kumari, “Performance analysis of off-line signature verification,” in International Conference on Innovative Computing and Communications, 2020, pp. 161–171, doi: 10.1007/978-981-15-1286-5_14.
[13] Taşkiran, M., & Çam, Z. G. (2017, January). Offline signature identification via HOG features and artificial neural networks. In 2017 IEEE 15th International Symposium on Applied Machine Intelligence and Informatics (SAMI) (pp. 000083-000086). IEEE.
[14] K. Daqrouq, H. Sweidan, A. Balamesh, and M. Ajour, “Off-line handwritten signature recognition by wavelet entropy and neural network,” Entropy, vol. 19, no. 6, p. 252, May 2017, doi: 10.3390/e19060252.
[15] Bhavani, S. D., Bharathi, R. K., & Kumar, R. J. (2024, March). Offline signature verification using pre-trained deep convolutional neural network. In AIP Conference Proceedings (Vol. 2966, No. 1). AIP Publishing.
[16] Bharathi, R. K., & Shekar, B. H. (2013, August). Off-line signature verification based on chain code histogram and support vector machine. In 2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 2063-2068). IEEE.
[17] Bharathi, R. K., & Shekar, B. H. (2014, September). Discriminative dct-mlp based approach for off-line signature verification. In 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 2309-2315). IEEE.
[18] Bhavani, S. D., Bharathi, R. K., & Kumar, R. J. (2024, March). Offline signature verification using pre-trained deep convolutional neural network. In AIP Conference Proceedings (Vol. 2966, No. 1). AIP Publishing.
© Published by INDEAMIND. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Bhavani S.D, Bharathi R.K. Exploring Various Feature Extraction Methods for Offline Signature Verification. Ind J Eng Mgt Sci. 2025;1(1):29-36