Fake Signature Recognition Using Convolutional Neural Network with ResNet-18 Architecture
DOI:
https://doi.org/10.59535/faase.v3i2.626Keywords:
Signature, Convolutional Neural Network, Resnet-18Abstract
Signatures are widely used as a personal identity marker and as a key element in validating official documents. Although each individual’s signature is generally distinctive, genuine signatures may vary in shape and size across different instances, while forged signatures can appear visually similar to authentic ones. These factors make manual verification subjective, time-consuming, and prone to error, particularly when handling large volumes of documents. This study developed an automatic signature recognition system using deep learning, specifically a Convolutional Neural Network (CNN) with a ResNet-18 architecture. The dataset consisted of 1,038 signature images, and model performance was evaluated across multiple training epochs. The best result was obtained using the Adam optimizer at epoch 25, achieving an accuracy of 59.5% on the evaluated data. The findings indicate that high visual similarity among signature images can substantially affect classification outcomes, suggesting that offline signature recognition remains challenging when formulated as a simple binary image classification task. Future work should consider improving the training protocol and evaluation scheme to better capture subtle discriminative features between genuine and forged signatures.
Downloads
References
M. Leghari et al., ‘Deep Feature Fusion of Fingerprint and Online Signature for Multimodal Biometrics’, Computers, vol. 10, no. 2, Feb. 2021, doi: 10.3390/computers10020021.
Y. Zhong et al., ‘Distributed Blockchain-Based Authentication and Authorization Protocol for Smart Grid’, Wireless Communications and Mobile Computing, vol. 2021, no. 1, p. 5560621, 2021, doi: 10.1155/2021/5560621.
H.-L. Yin et al., ‘Experimental quantum secure network with digital signatures and encryption’, Natl Sci Rev, vol. 10, no. 4, p. nwac228, Apr. 2023, doi: 10.1093/nsr/nwac228.
A. Alnuaim, M. Zakariah, W. A. Hatamleh, H. Tarazi, V. Tripathi, and E. T. Amoatey, ‘Human-Computer Interaction with Hand Gesture Recognition Using ResNet and MobileNet’, Computational Intelligence and Neuroscience, vol. 2022, no. 1, p. 8777355, 2022, doi: 10.1155/2022/8777355.
W. N. Ismail, H. A. Alsalamah, M. M. Hassan, and E. Mohamed, ‘AUTO-HAR: An adaptive human activity recognition framework using an automated CNN architecture design’, Heliyon, vol. 9, no. 2, Feb. 2023, doi: 10.1016/j.heliyon.2023.e13636.
E. Jing, H. Zhang, Z. Li, Y. Liu, Z. Ji, and I. Ganchev, ‘ECG Heartbeat Classification Based on an Improved ResNet-18 Model’, Computational and Mathematical Methods in Medicine, vol. 2021, no. 1, p. 6649970, 2021, doi: 10.1155/2021/6649970.
Q. Xie, X. Wang, H. Sun, Y. Zhang, and X. Lu, ‘[Retracted] ECG Signal Detection and Classification of Heart Rhythm Diseases Based on ResNet and LSTM’, Advances in Mathematical Physics, vol. 2021, no. 1, p. 5862017, 2021, doi: 10.1155/2021/5862017.
W. Liu et al., ‘Automated echocardiogram image quality assessment with YOLO and resnet in the left ventricular myocardium of A4C views’, Appl Intell, vol. 55, no. 7, p. 513, Mar. 2025, doi: 10.1007/s10489-025-06419-z.
M. J. Curtis et al., ‘Planning experiments: Updated guidance on experimental design and analysis and their reporting III’, British Journal of Pharmacology, vol. 179, no. 15, pp. 3907–3913, 2022, doi: 10.1111/bph.15868.
M. Reyad, A. M. Sarhan, and M. Arafa, ‘A modified Adam algorithm for deep neural network optimization’, Neural Comput & Applic, vol. 35, no. 23, pp. 17095–17112, Aug. 2023, doi: 10.1007/s00521-023-08568-z.
E. Hassan, M. Y. Shams, N. A. Hikal, and S. Elmougy, ‘The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study’, Multimed Tools Appl, vol. 82, no. 11, pp. 16591–16633, May 2023, doi: 10.1007/s11042-022-13820-0.
U. Ahmed et al., ‘Signature-based intrusion detection using machine learning and deep learning approaches empowered with fuzzy clustering’, Sci Rep, vol. 15, no. 1, p. 1726, Jan. 2025, doi: 10.1038/s41598-025-85866-7.
A. Golkarieh, P. Razmara, A. Lagzian, A. Dolatabadi, and S. J. Mousavirad, ‘Semi-supervised GAN with hybrid regularization and evolutionary hyperparameter tuning for accurate melanoma detection’, Sci Rep, vol. 15, no. 1, p. 31977, Aug. 2025, doi: 10.1038/s41598-025-17756-x.
Y. Hui Min and W. Waemustafa, ‘Unveiling the Anatomy of Banking Crises: A Comprehensive Analysis of Systemic Vulnerabilities and Contributing Factors in the United States’, Mar. 24, 2024, Social Science Research Network, Rochester, NY: 4770676. doi: 10.2139/ssrn.4770676.
R. Elanwar and M. Betke, ‘Generative adversarial networks for handwriting image generation: a review’, Vis Comput, vol. 41, no. 4, pp. 2299–2322, Mar. 2025, doi: 10.1007/s00371-024-03534-9.
J. S. Wang, ‘Exploring biometric identification in FinTech applications based on the modified TAM’, Financ Innov, vol. 7, no. 1, p. 42, Jun. 2021, doi: 10.1186/s40854-021-00260-2.
V. Rajasekar et al., ‘Enhanced multimodal biometric recognition approach for smart cities based on an optimized fuzzy genetic algorithm’, Sci Rep, vol. 12, no. 1, p. 622, Jan. 2022, doi: 10.1038/s41598-021-04652-3.
S. Mekruksavanich, A. Jitpattanakul, S. Mekruksavanich, and A. Jitpattanakul, ‘Biometric User Identification Based on Human Activity Recognition Using Wearable Sensors: An Experiment Using Deep Learning Models’, Electronics, vol. 10, no. 3, Jan. 2021, doi: 10.3390/electronics10030308.
Y. Arouri and M. Sayyafzadeh, ‘An adaptive moment estimation framework for well placement optimization’, Comput Geosci, vol. 26, no. 4, pp. 957–973, Aug. 2022, doi: 10.1007/s10596-022-10135-9.
M. Liu, D. Yao, Z. Liu, J. Guo, and J. Chen, ‘An Improved Adam Optimization Algorithm Combining Adaptive Coefficients and Composite Gradients Based on Randomized Block Coordinate Descent’, Computational Intelligence and Neuroscience, vol. 2023, no. 1, p. 4765891, 2023, doi: 10.1155/2023/4765891.
Z. Liu, R. Feng, X. Li, W. Wang, and X. Wu, ‘Gradient-Sensitive Optimization for Convolutional Neural Networks’, Computational Intelligence and Neuroscience, vol. 2021, no. 1, p. 6671830, 2021, doi: 10.1155/2021/6671830.
L. Galke, Y. Ram, and L. Raviv, ‘Deep neural networks and humans both benefit from compositional language structure’, Nat Commun, vol. 15, no. 1, p. 10816, Dec. 2024, doi: 10.1038/s41467-024-55158-1.
E. S. Dietrich, ‘Artificial intelligence in key pricing, reimbursement, and market access (PRMA) processes: better, faster, cheaper—can you really pick two?’, Journal of Medical Economics, vol. 28, no. 1, pp. 586–595, Dec. 2025, doi: 10.1080/13696998.2025.2488154.
J. Liu et al., ‘TriCTI: an actionable cyber threat intelligence discovery system via trigger-enhanced neural network’, Cybersecurity, vol. 5, no. 1, p. 8, Apr. 2022, doi: 10.1186/s42400-022-00110-3.
A. A. H. de Hond et al., ‘Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review’, npj Digit. Med., vol. 5, no. 1, p. 2, Jan. 2022, doi: 10.1038/s41746-021-00549-7.
S. A. Hicks et al., ‘On evaluation metrics for medical applications of artificial intelligence’, Sci Rep, vol. 12, no. 1, p. 5979, Apr. 2022, doi: 10.1038/s41598-022-09954-8.
P. Sharma, M. Kumar, H. K. Sharma, and S. M. Biju, ‘Generative adversarial networks (GANs): Introduction, Taxonomy, Variants, Limitations, and Applications’, Multimed Tools Appl, vol. 83, no. 41, pp. 88811–88858, Dec. 2024, doi: 10.1007/s11042-024-18767-y.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Abdul Aziz Al Basyir, Kenan Almas, Big Daya Yudha Asmara
This work is licensed under a Creative Commons Attribution 4.0 International License.
By submitting a manuscript to Frontier Advances in Applied Science and Engineering (FAASE), the author(s) agree to the following terms:
-
Copyright: The author(s) retain copyright to their work, granting Frontier Advances in Applied Science and Engineering (FAASE) the right to publish it. Articles are licensed under a Creative Commons Attribution 4.0 International License (CC BY).
-
License Grant: The CC BY license allows others to share and adapt the work for any purpose, even commercially, provided proper attribution is given to the original author(s) and the source, a link to the Creative Commons license is provided, and any changes made are indicated.
-
Author's Rights: Authors are allowed to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work, with proper acknowledgment of its initial publication in Frontier Advances in Applied Science and Engineering (FAASE).
-
Permissions: Reproduction, posting, transmission, or other distribution or use of the final published article, in whole or in part, requires prior written permission from Frontier Advances in Applied Science and Engineering (FAASE) and the respective author(s).
-
Attribution: Proper attribution must be given to the original author(s) and the source, indicating that the work was originally published in Frontier Advances in Applied Science and Engineering (FAASE) with a link to the published article.
-
No Warranty: The journal and its editorial team make no representations or warranties regarding the accuracy, completeness, or fitness for a particular purpose of the published work.
-
Dispute Resolution: Any disputes arising from the use of the licensed material shall be governed by the laws of [Jurisdiction] without regard to conflicts of law principles.
By submitting a manuscript to FAASE, the author(s) agree to abide by these license terms and grant the necessary rights to Frontier Advances in Applied Science and Engineering (FAASE) for the publication and dissemination of the submitted work.
