Automated Signature Authentication Using Deep Convolutional Neural Network
Article Sidebar
Main Article Content
Abstract
Verifying the authenticity of handwritten signatures remains a vital challenge in biometric security systems, especially in financial, legal, and administrative domains. This work presents a deep learning–based framework for automated offline signature authentication using transfer learning with MobileNetV2. The system distinguishes real from forged signatures through convolutional feature extraction and classification. Leveraging MobileNetV2’s lightweight architecture and ImageNet pretraining, the model is fine-tuned on a labelled signature dataset using data augmentation and adaptive training. The pipeline consists of four core modules: Data Preprocessing, CNN Feature Extraction, Transfer Learning Fine-Tuning, and Real-Time Signature Prediction. Evaluation on a real-world dataset achieves 96.46% accuracy, as shown in the confusion matrix. This framework provides a reliable, scalable solution for signature verification in practical security applications, especially where computational efficiency and high precision are essential.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
S.-J. Chang and T.-R. Wu, “Development of a signature verification model based on a small number of samples,” Signal, Image and Video Processing, vol. 18, pp. 285–294, 2024.
DOI: 10.1007/s11760-023-02714-9
B. Ribeiro, I. Gonçalves, S. Santos, and A. Kovacec, "Deep Learning Networks for Off-Line Handwritten Signature Recognition," in Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, CIARP 2011, LNCS 7042, Springer, 2011, pp. 491–498, DOI: 10.1007/978-3-642-25085-9_62.
U. Umair, "A Deep Insight into Signature Verification Using Deep Neural Network," in Intelligent Systems and Applications, Advances in Intelligent Systems and Computing, vol. 1222, Springer, 2020, pp. 91–103, DOI: 10.1007/978-3-030-55190-2_10.
M. Diaz, M. A. Ferrer, and G. Vessio, "Explainable Offline Automatic Signature Verifier to Support Forensic Handwriting Examiners," Neural Computing and Applications, vol. 35, pp. 7119–7133, 2023, DOI: 10.1007/s00521-023-09192-7.
Nisha Chaurasia and Ishu Priya Fuzzy, “CNN-Based Framework for Handwritten Signature Verification," in Advances in Data Science and Intelligent Systems, Springer, 2024,
DOI: 10.1007/978-3-031-90998-6_16.
H. Lu, C. Chen, and M. Zhang, “Deep Learning-Based Data Augmentation Method and Signature Verification System for Offline Handwritten Signature," in Lecture Notes in Computer Science, Springer. DOI: 10.3390/app12199904
Z. Liu, L. Wang, and S. Zhang, "Lightweight Object Detection Algorithm Based on YOLOv5 for USVs," Frontiers in Marine Science, vol. 9, 2022, DOI:10.3389/fmars.2022.1058401.
Zois, E., Alexandridis, A., Economou, G.: “Writer-independent offline signature verification based on asymmetric pixel relations and unrelated training-testing datasets”. Expert Syst. Appl. 125, 14–32 (2019). DOI: 10.1016/j.eswa.2019.01.058
Hameed, M.M., Ahmad, R., Kiah, M.L.M., Murtaza, G.: “Machine learning-based offline signature verification systems: a systematic review”. Signal Process. Image Commu. 93, 116139 (2021). https://www.sciencedirect.com/science/article/pii/S0923596521000047
Ghosh, R.: “A recurrent neural network-based deep learning model for offline signature verification and recognition system”. Expert Syst. Appl. 168, 114249(2021). DOI: 10.1016/j.eswa.2021.116136
C. Boschini et al., "Progressive and Efficient Verification for Digital Signatures: Extensions and Experimental Results," in Journal of Cryptographic Engineering, vol. 14, no. 3, pp. 285-312, Aug. 2024. https://research.chalmers.se/publication/542324/file/542324_Fulltext.pdf
A. Christianto et al., "Authentic Signature Verification Using Deep Learning Embedding with Triplet Loss Optimisation and Machine Learning Classification," in International Journal of Computing and Digital Systems, vol. 16, no. 1, pp. 122-132, Jul. 2024.
https://journal.uob.edu.bh/items/8e49ed1c-73e7-4c29-bb15-7c828b9619a1
H. P. Kaur and M. Kumar, "Signature Identification and Verification Techniques: State-of-the-Art Work," in Journal of Ambient Intelligence and Humanised Computing, vol. 14, pp. 1027-1045, 2021.
DOI: 10.1016/j.eswa.2025.127646
R. Alrawili et al., "Comprehensive Survey: Biometric User Authentication Application, Evaluation, and Discussion," in IEEE Access, vol. 12, pp. 17845-17868, Nov. 2023.
DOI: 10.48550/arXiv.2311.13416
Gunasinghe et al., "Bias: A Novel Secure and Efficient Biometrics-Based Identity Authentication Scheme," in IACR Transactions on Information Security, vol. 18, no. 2, pp. 47-59, May 2024.
DOI: 10.1016/j.comnet.2024.110754
Z. Rui and Z. Yan, "A Survey on Biometric Authentication: Toward Secure and Privacy-Preserving Identification," in IEEE Access, vol. 7, pp. 5994-6009, Jan. 2019.
DOI: 10.1007/978-3-030-71522-9_734
A.-K. Al-Tamimi et al., "Offline Signature Recognition System Using Oriented FAST and Rotated BRIEF," in International Journal of Electrical and Computer Engineering, vol. 11, no. 5, pp. 4095-4103, Oct. 2021.
https://shura.shu.ac.uk/31045/1/OfflineSignatureRecognition.pdf
M. V. Diaz et al., "Explainable Offline Automatic Signature Verifier to Support Forensic Handwriting Examiners," in Neural Computing and Applications, vol. 35, pp. 7119-7133,
DOI: 10.48550/arXiv.2405.12695
G. Chen et al., "An Eye Blink Based Biometric Authentication System Using Transient Eye Blink Signals," in IEEE Transactions on Automation Science and Engineering, vol. 18, no. 2, pp. 534-545, 2021. https://mediatum.ub.tum.de/doc/1638461/jc29733kp744fkne500mz6e7m.jas.2020.1003483.pdf
S. Srihari and A. Xu, "Offline Signature Verification and Identification Using Distance Statistics," in International Journal of Pattern Recognition and Artificial Intelligence, vol. 18, no. 7, pp. 1339-1360, Nov. 2004.
https://ijcaonline.org/archives/volume79/number2/13717-1489/, works remain significant; see the declaration
A. Aljrami et al., "Dynamic Signature Verification Using Pattern Recognition," in Journal of Software Engineering and Applications, vol. 17, no. 5, pp. 312-326, May 2024.
https://www.scirp.org/pdf/jsea2024175_29303242.pdf
L. Zhang et al., "Learning Features for Offline Handwritten Signature Verification Using Siamese Networks," in Scientific Reports, vol. 15, no. 24, pp. 11545-11560, Mar. 2025.
https://pmc.ncbi.nlm.nih.gov/articles/PMC11923077/
S. Gunasinghe et al., "Secure Authentication Protocols Using Biometric Data," in Advances in Information Security, vol. 21, pp. 239-252, Oct. 2024.
https://www.researchgate.net/publication/385446674
P. Gupta et al., "Advancing Handwritten Signature Verification Through YOLOv5 and Deep Learning Approaches," in International Journal of Engineering Trends and Technology, vol. 72, no. 4, pp. 110-116, Apr. 2024.
https://ijettjournal.org/Volume-72/Issue-4/IJETT-V72I4P109.pdf
A. K. Al-Tamimi et al., "Offline Writer Independent Handwritten Signature Verification System," in International Journal of Advanced Research in Computer and Communication Engineering, vol. 12, no. 2, pp. 151-160, Feb. 2023.
DOI: 10.1109/ICCIT54785.2021.9689780