DOI: 10.12732/ijam.v38i2.12
HYBRID OFFLINE-ONLINE SIGNATURE
VERIFICATION WITH CROSS-WRITER MISMATCH
MODELLING AND FUZZY FUSION
Anjali Rohilla1, Rajesh Kumar Bawa2
1Department of Computer Science
Punjabi University
Patiala, India
2Department of Computer Science
Punjabi University
Patiala, India
Abstract. This paper presents a hybrid signature verification framework integrating offline handwritten signature images and online dynamic signing information for reliable biometric authentication. Offline signatures are represented using structural gradient-based descriptors, while online signatures are characterised through temporal and statistical features extracted from log trajectories. Both modalities are fused into a unified feature space, normalised, and reduced using principal component analysis for efficient learning. Writer independent evaluation is performed using group-based cross validation with cross-writer mismatch modelling to strengthen resistance against multimodal forgery attempts. Random Forest and Gradient Boosting classifiers are trained and combined through ensemble probability fusion, while fuzzy membership based decision support improves stability under uncertain verification conditions. Experimental results show competitive writer-independent accuracy with very low false rejection and equal error rates, confirming the effectiveness of multimodal fusion and fuzzy ensemble learning. The proposed framework provides a practical and robust solution for secure signature-based authentication systems.
How
to cite this paper?
Source: International Journal of Applied Mathematics
ISSN printed version: 1311-1728
ISSN on-line version: 1314-8060
Year: 2025
Volume: 38
Issue: 2
References
[1] W. Li, M. Muhammat, X. Xu, et al., “Multi-scale CNNCrossViT network for offline handwritten signature recognition and verification,” Complex & Intelligent Systems, vol. 11, p. 400, 2025, doi: 10.1007/s40747-025-02011-7.
[2] W. Xiao and H. Wu, “Learning features for offline handwritten signature verification using spatial transformer network,” Scientific Reports, vol. 15, p. 9453, 2025, doi: 10.1038/s41598-025-92704-3.
[3] F. Khan, M. Tahir, and F. Khelifi, “Robust offline text independent writer identification using bagged discrete cosine transform features,” Expert Systems with Applications, vol. 71, pp. 404-415, 2017.
[4] L. Wei, L. Jin, and X. Luo, “A robust coevolutionary neuralbased optimization algorithm for constrained nonconvex optimization,” IEEE Transactions on Neural Networks and Learning Systems, 2022, doi: 10.1109/TNNLS.2022.3220806.
[5] H. Li, P. Wei, and P. Hu, “AVN: An adversarial variation network model for handwritten signature verification,” IEEE Transactions on Multimedia, vol. 24, pp. 594-608, 2021, doi: 10.1109/TMM.2021.3056217.
[6] X. Lu, L. Huang, and F. Yin, “Cut and compare: End-toend offline signature verification network,” in Proc. 25th Int. Conf. Pattern Recognition (ICPR), Milan, Italy, pp. 3589-3596, 2020, doi: 10.1109/ICPR48806.2021.9412377.
[7] A. Jain, S. K. Singh, and K. P. Singh, “Handwritten signature verification using shallow convolutional neural network,” Multimedia Tools and Applications, vol. 79, pp. 19993-20018, 2020.
[8] J. Zhang et al., “Water body detection in high-resolution SAR images with cascaded fully-convolutional network and variable focal loss,” IEEE Transactions on Geoscience and Remote Sensing, vol. 59, pp. 316-332, 2021.
[9] X. Luo, H. Wu, and Z. Li, “NeuLFT: A novel approach to nonlinear canonical polyadic decomposition on high-dimensional incomplete tensors,” IEEE Transactions on Knowledge and Data Engineering, 2022, doi: 10.1109/TKDE.2022.3176466.
[10] E. N. Zois, L. Alewijnse, and G. Economou, “Offline signature verification and quality characterization using poset-oriented grid features,” Pattern Recognition, vol. 54, pp. 162-177, 2016.
[11] R. K. Bharathi and B. H. Shekar, “Offline signature verification based on chain code histogram and support vector machine,” in Proc. Int. Conf. Advances in Computing, Communications and Informatics (ICACCI), Mysore, India, pp. 2063-2068, 2013.
[12] P. Maergner, V. Pondenkandath, M. Alberti, M. Liwicki, and K. Riesen, “Combining graph edit distance and triplet networks for offline signature verification,” Pattern Recognition Letters, vol. 125, pp. 527-533, 2019.
[13] D. Wu, Q. He, X. Luo, and M. Zhou, “A latent factor analysisbased approach to online sparse streaming feature selection,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, doi: 10.1109/TSMC.2021.3096065.
[14] A. Alaei, S. Pal, U. Pal, and M. Blumenstein, “An efficient signature verification method based on an interval symbolic representation and a fuzzy similarity measure,” IEEE Transactions on Information Forensics and Security, vol. 10, no. 12, pp. 2360-2372, 2017.
[15] X. Luo, Y. Zhou, Z. Liu, and M. Zhou, “Generalized Nesterov’s acceleration-incorporated, non-negative and adaptive latent factor analysis,” IEEE Transactions on Services Computing, vol. 15, no. 5, pp. 2809-2823, 2022.
[16] A. Jain, S. K. Singh, and K. P. Singh, “Multi-task learning using GNet features and SVM classifier for signature identification,” IET Biometrics, vol. 2, pp. 117-126, 2021.
[17] Z. Liu, G. Yuan, and X. Luo, “Symmetry and nonnegativityconstrained matrix factorization for community detection,” IEEE/CAA Journal of Automatica Sinica, vol. 9, no. 9, pp. 1691-1693, 2022.
[18] M. Sharif, M. Khan, M. Faisal, M. Yasmin, and S. L. Fernandes, “A framework for offline signature verification system: Best features selection approach,” Pattern Recognition, vol. 139, p. 50-59, 2020.
[19] F. Khan, M. Tahir, and F. Khelifi, “Novel geometric features for offline writer identification,” Pattern Analysis and Applications, vol. 19, pp. 699-708, 2016.
[20] A. K. Bhunia, A. Alaei, and P. P. Roy, “Signature verification approach using fusion of hybrid texture features,” Neural Computing and Applications, vol. 31, pp. 8737-8748, 2019.
[21] C. R. Chen, Q. Fan, and R. Panda, “CrossViT: Crossattention multi-scale vision transformer for image classification,” in Proc. IEEE/CVF Int. Conf. Computer Vision (ICCV), Montreal, Canada, pp. 347-356, 2021, doi: 10.1109/ICCV48922.2021.00041.
[22] R. Ghosh, “A recurrent neural network based deep learning model for offline signature verification and recognition system,” Expert Systems with Applications, vol. 168, p. 114249, 2021, doi: 10.1016/J.ESWA.2020.114249.
[23] F. E. Batool et al., “Offline signature verification system: A novel technique of fusion of GLCM and geometric features using SVM,” Multimedia Tools and Applications, vol. 83, no. 5, pp. 14959-14978, 2024.
[24] F. ¨ Ozyurt, J. Majidpour, T. A. Rashid, and C. Koc, “Offline handwriting signature verification: A transfer learning and feature selection approach,” arXiv:2401.09467, 2024, doi: 10.48550/ARXIV.2401.09467.
[25] T. Longjam, D. R. Kisku, and P. Gupta, “Writer independent handwritten signature verification on multi-scripted signatures using hybrid CNN-BiLSTM: A novel approach,” Expert Systems with Applications, vol. 214, p. 119111, 2023, doi: 10.1016/J.ESWA.2022.119111.
[26] X. Cairang et al., “Learning generalisable representations for offline signature verification,” in Proc. Int. Joint Conf. Neural Networks (IJCNN), Padua, Italy, pp. 1-7, 2022, doi: 10.1109/IJCNN55064.2022.98922.
IJAM
o Home
o Contents