Leveraging deep feature learning for handwriting biometric authentication

Afzali, Parvaneh; Rezapour, Abdoreza; Rezaee Jordehi, Ahmad

doi:10.22105/riej.2024.432510.1412

Document Type : Research Paper

Authors

¹ Department of Computer Engineering, Rasht Branch, Islamic Azad University, Rasht, Iran.

² Department of Computer Engineering, Astaneh Ashrafieh Branch, Islamic Azad University, Astaneh Ashrafieh, Iran.

³ Department of Electrical Engineering, Rasht Branch, Islamic Azad University, Rasht, Iran.

https://doi.org/10.22105/riej.2024.432510.1412

Abstract

The authentication of writers through handwritten text stands as a biometric technique with considerable practical importance in the field of document forensics and literary history. The verification process involves a meticulous examination of the questioned handwriting in comparison to the genuine handwriting of a known writer, aiming to determine whether a shared authorship exists. In real-world scenarios, writer verification based on the handwritten text presents more challenges compared to signatures. Signatures typically consist of fixed designs chosen by signers, whereas textual content can vary and encompass a diverse set of letters, numbers, and punctuation marks. Moreover, verifying a writer based on limited handwritten texts, such as a single word, is recognized as one of authentication's open and challenging aspects. In this paper, we propose a Customized Siamese Convolutional Neural Network (CSCNN) for offline writer verification based on handwritten words. Additionally, a combined loss function is employed to achieve more accurate discrimination between the handwriting styles of different writers. The designed model is trained with pairs of images, each comprising one authentic and one questioned handwritten word. The effectiveness of the proposed model is substantiated through experimental results obtained from two well-known datasets in both English and Arabic, IAM and IFN/ENIT. These results underscore the efficiency and performance of our model across diverse linguistic contexts.

Keywords

Main Subjects

Machine Learning

References

[1] Shaikh, M. A., Chauhan, M., Chu, J., & Srihari, S. (2018). Hybrid feature learning for handwriting verification. 2018 16th international conference on frontiers in handwriting recognition (ICFHR) (pp. 187–192). IEEE. DOI: 10.1109/ICFHR-2018.2018.00041

[2] Khan, F. A., Khelifi, F., Tahir, M. A., & Bouridane, A. (2019). Dissimilarity gaussian mixture models for efficient offline handwritten text-independent identification using SIFT and root SIFT descriptors. IEEE transactions on information forensics and security, 14(2), 289–303. DOI:10.1109/TIFS.2018.2850011

[3] Çalik, N., Kurban, O. C., Yilmaz, A. R., Yildirim, T., & Durak Ata, L. (2019). Large-scale offline signature recognition VIA deep neural networks and feature embedding. Neurocomputing, 359, 1–14. https://www.sciencedirect.com/science/article/pii/S0925231219303674

[4] Parcham, E., Ilbeygi, M., & Amini, M. (2021). CBCapsNet: a novel writer-independent offline signature verification model using a CNN-based architecture and capsule neural networks. Expert systems with applications, 185, 115649. https://www.sciencedirect.com/science/article/pii/S095741742101040X

[5] Xiong, Y. J., Lu, Y., & Wang, P. S. P. (2017). Off-line text-independent writer recognition: a survey. International journal of pattern recognition and artificial intelligence, 31(5), 1756008. https://doi.org/10.1142/S0218001417560080

[6] Yılmaz, M. B., & Yanıkoğlu, B. (2016). Score level fusion of classifiers in off-line signature verification. Information fusion, 32, 109–119. https://www.sciencedirect.com/science/article/pii/S1566253516300033

[7] Bensefia, A., & Paquet, T. (2016). Writer verification based on a single handwriting word samples. Eurasip journal on image and video processing, 2016(1), 34. https://doi.org/10.1186/s13640-016-0139-0

[8] Hafemann, L. G., Sabourin, R., & Oliveira, L. S. (2017). Learning features for offline handwritten signature verification using deep convolutional neural networks. Pattern recognition, 70, 163–176. https://www.sciencedirect.com/science/article/pii/S0031320317302017

[9] Dey, S., Dutta, A., Toledo, J. I., Ghosh, S. K., Lladós, J., & Pal, U. (2017). Signet: convolutional siamese network for writer independent offline signature verification. https://arxiv.org/abs/1707.02131

[10] Jang, W., Kim, S., Kim, Y., & Lee, E. C. (2018). Automated verification method of korean word handwriting using geometric feature. Advances in computer science and ubiquitous computing (pp. 1340–1345). Singapore: springer singapore.

[11] Adak, C., Marinai, S., Chaudhuri, B. B., & Blumenstein, M. (2018). Offline bengali writer verification by pdf-cnn and siamese net. 2018 13th iapr international workshop on document analysis systems (DAS) (pp. 381–386). IEEE. DOI: 10.1109/DAS.2018.33

[12] Maergner, P., Pondenkandath, V., Alberti, M., Liwicki, M., Riesen, K., Ingold, R., & Fischer, A. (2019). Combining graph edit distance and triplet networks for offline signature verification. Pattern recognition letters, 125, 527–533. https://www.sciencedirect.com/science/article/pii/S0167865519301850

[13] Ghosh, R. (2021). A recurrent neural network based deep learning model for offline signature verification and recognition system. Expert systems with applications, 168, 114249. https://www.sciencedirect.com/science/article/pii/S0957417420309659

[14] Yapıcı, M. M., Tekerek, A., & Topaloğlu, N. (2021). Deep learning-based data augmentation method and signature verification system for offline handwritten signature. Pattern analysis and applications, 24(1), 165–179. https://doi.org/10.1007/s10044-020-00912-6

[15] Aubin, V., Mora, M., & Santos, M. (2022). A new approach for writer verification based on segments of handwritten graphemes. Logic journal of the igpl, 30(6), 965–978. https://doi.org/10.1093/jigpal/jzac006

[16] Khan, M. A., Mohammad, N., Brahim, G. Ben, Bashar, A., & Latif, G. (2022). Writer verification of partially damaged handwritten Arabic documents based on individual character shapes. PeerJ computer science, 8, 1–28. https://peerj.com/articles/cs-955/

[17] Sadr, H., & Nazari Soleimandarabi, M. (2022). ACNN-TL: attention-based convolutional neural network coupling with transfer learning and contextualized word representation for enhancing the performance of sentiment classification. The journal of supercomputing, 78(7), 10149–10175. https://doi.org/10.1007/s11227-021-04208-2

[18] Javidi, M., & Jampour, M. (2020). A deep learning framework for text-independent writer identification. Engineering applications of artificial intelligence, 95, 103912. https://www.sciencedirect.com/science/article/pii/S0952197620302463

[19] Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., … & Farhan, L. (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of big data, 8(1), 8-53. https://doi.org/10.1186/s40537-021-00444-8

[20] Chakladar, D. Das, Kumar, P., Roy, P. P., Dogra, D. P., Scheme, E., & Chang, V. (2021). A multimodal-siamese neural network (MSNN) for person verification using signatures and EEG. Information fusion, 71, 17–27. https://www.sciencedirect.com/science/article/pii/S1566253521000105

[21] Dubey, S. R., Singh, S. K., & Chaudhuri, B. B. (2022). Activation functions in deep learning: a comprehensive survey and benchmark. Neurocomputing, 503, 92–108. https://www.sciencedirect.com/science/article/pii/S0925231222008426

[22] Beke, A., & Kumbasar, T. (2019). Learning with type-2 fuzzy activation functions to improve the performance of deep neural networks. Engineering applications of artificial intelligence, 85, 372–384. https://www.sciencedirect.com/science/article/pii/S0952197619301551

[23] Zhang, Q., Pei, M., Chen, M., & Jia, Y. (2018). Vehicle verification based on deep siamese network with similarity metric. Advances in multimedia information processing-PCM 2017 (pp. 773–782). Cham: springer international publishing. https://doi.org/10.1007/978-3-319-77380-3_74

[24] Tian, Y., Su, D., Lauria, S., & Liu, X. (2022). Recent advances on loss functions in deep learning for computer vision. Neurocomputing, 497, 129–158. https://www.sciencedirect.com/science/article/pii/S0925231222005239

[25] Wang, F., & Liu, H. (2021). Understanding the behaviour of contrastive loss. 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR) (pp. 2495–2504). IEEE. DOI: 10.1109/CVPR46437.2021.00252

[26] De Boer, P. T., Kroese, D. P., Mannor, S., & Rubinstein, R. Y. (2005). A tutorial on the cross-entropy method. Annals of operations research, 134(1), 19–67. https://doi.org/10.1007/s10479-005-5724-z

[27] Marti, U. V., & Bunke, H. (2002). The IAM-database: an english sentence database for offline handwriting recognition. International journal on document analysis and recognition, 5(1), 39–46. https://doi.org/10.1007/s100320200071

[28] El Abed, H., & Margner, V. (2007). The ifn/enit-database-a tool to develop arabic handwriting recognition systems. 2007 9th international symposium on signal processing and its applications (pp. 1–4). IEEE. DOI: 10.1109/ISSPA.2007.4555529

International Journal of Research in Industrial Engineering

Leveraging deep feature learning for handwriting biometric authentication

References

References

Volume 13, Issue 1
March 2024
Pages 88-103

Leveraging deep feature learning for handwriting biometric authentication

References

References

Volume 13, Issue 1March 2024Pages 88-103

Volume 13, Issue 1
March 2024
Pages 88-103