Volume 24 , Issue 2 , PP: 268-282, 2024 | Cite this article as | XML | Html | PDF | Full Length Article
Oday Ali Hassen 1 * , Shahlaa Mashhadani 2 , Iptehaj Alhakam 3 , Saad M. Darwish 4
Doi: https://doi.org/10.54216/IJNS.240224
One of the most popular and legally recognized behavioral biometrics is the individual's signature, which is used for verification and identification in many different industries, including business, law, and finance. The purpose of the signature verification method is to distinguish genuine from forged signatures, a task complicated by cultural and personal variances. Analysis, comparison, and evaluation of handwriting features are performed in forensic handwriting analysis to establish whether or not the writing was produced by a known writer. In contrast to other languages, Arabic makes use of diacritics, ligatures, and overlaps that are unique to it. Due to the absence of dynamic information in the writing of Arabic signatures, it will be more difficult to attain greater verification accuracy. On the other hand, the characteristics of Arabic signatures are not very clear and are subject to a great deal of variation (features’ uncertainty). To address this issue, the suggested work offers a novel method of verifying offline Arabic signatures that employs two layers of verification, as opposed to the one level employed by prior attempts or the many classifiers based on statistical learning theory. A static set of signature features is used for layer one verification. The output of a neutrosophic logic module is used for layer two verification, with the accuracy depending on the signature characteristics used in the training dataset and on three membership functions that are unique to each signer based on the degree of truthiness, indeterminacy, and falsity of the signature features. The three memberships of the neutrosophic set are more expressive for decision-making than those of the fuzzy sets. The purpose of the developed model is to account for several kinds of uncertainty in describing Arabic signatures, including ambiguity, inconsistency, redundancy, and incompleteness. The experimental results show that the verification system works as intended and can successfully reduce the FAR and FRR.
Signature forensics , neutrosophic reasoning , offline signature verification , decision making under uncertainty , context-based verification.
[1] Dhieb, T., Boubaker, H., Njah, S., Ben Ayed, M., Alimi. A. A novel biometric system for signature verification based on score level fusion approach. Multimedia Tools and Applications, 81(6):7817-7845. 2022.
[2] Huang, J., Xue, Y., Liu, L. Dynamic signature verification technique for the online and offline representation of electronic signatures in biometric systems. Processes, 11(1):1-18, 190, 2023.
[3] Jagtap, A., Sawat, D., Hegadi, R. Review on offline signature verification: datasets, methods and challenges. In Proceedings of Third International Conference of the Recent Trends in Image Processing and Pattern Recognition, India, Revised Selected Papers, Part I 3, pp. 458-468, Springer Singapore, 2021.
[4] Paul, J., Dutta, K., Sarkar, A., Das, N., Roy, K. A survey on different feature extraction methods for writer identification and verification. International Journal of Applied Pattern Recognition, 7(2):122-144, 2023.
[5] Alobaidi, A., Dhieb, T., Hamdani, T., Wali, A., Ouahada, K., Alimi, A. In-air signature verification system based on beta-elliptical approach and fuzzy perceptual detector, IEEE Access, 11(12):134058-134073, 2023.
[6] El-Douh, A., Lu, S., Abdelhafeez, A., Ali, A., Aziz, A. Neutrosophic model for evaluation healthcare security criteria for powerful and lightweight secure storage system in cloud-based e-healthcare services. Neutrosophic Sets and System, 58(1): 367- 378, 22, 2023.
[7] Hefny, A., Hassanien, A., Basha, S. Neutrosophic rule-based identity verification system based on handwritten dynamic signature analysis. Computers, Materials & Continua, 69(2): 2367-2385, 2021.
[8] Alqarni, M., Samak, A., Ismail, S., Abd El-Aziz, R., Taloba, A. Utilizing a neutrosophic fuzzy logic system with ANN for short-term estimation of solar energy. International Journal of Neutrosophic Science, 20(4):240-240, 2023.
[9] Zhang, K., Xie, Y., Noorkhah, S., Imeni, M., Das, S. Neutrosophic management evaluation of insurance companies by a hybrid TODIM-BSC method: a case study in private insurance companies. Management decision, 61(2):363-381, 2023.
[10] Aytekin, A., Okoth, B., Korucuk, S., Karamaşa, Ç. Tirkolaee, E. A neutrosophic approach to evaluate the factors affecting performance and theory of sustainable supply chain management: application to textile industry. Management Decision, 61(2):506-529, 2023.
[11] Mohamed, S., Abdel-Monem, A., Tantawy, A. Neutrosophic MCDM methodology for risk assessment of autonomous underwater vehicles. Neutrosophic Systems with Applications, 5(1):44-52, 2023.
[12] Rehman, A., Naz, S., Razzak, M. Writer identification using machine learning approaches: a comprehensive review. Multimedia Tools and Applications. 78(4):10889-10931, 2019.
[13] Abdulhussien, A., Nasrudin, M., Darwish, S., Alyasseri, ZA. Feature selection method based on quantum inspired genetic algorithm for Arabic signature verification. Journal of King Saud University-Computer and Information Sciences, 35(3):141-156, 2023.
[14] Alharbi, I. Efficient handwritten signatures identification using machine learning. International Journal of Advanced Computer Science and Applications, 14(3):141-148, 2023.
[15] Zhou, Y., Zheng, J., Hu, H., Wang, Y. Handwritten signature verification method based on improved combined features. Applied Sciences. 11(13):1-14, 5867, 2021.
[16] Longjam, T., Kisku, D., Gupta, P. Multi-scripted writer independent off-line signature verification using convolutional neural network. Multimedia Tools and Applications, 82(4):5839-5856, 2023.
[17] Chang, S., Wu, T. Development of a signature verification model based on a small number of samples. Signal, Image and Video Processing, vol.2023, pp-1-10, 2023.
[18] Alsuhimat, F., Mohamad, F. A Hybrid method of feature extraction for signatures verification using CNN and HOG a multi-classification approach. IEEE Access, 11(1):21873-21882, 2023.
[19] Keykhosravi, D., Razavi, S., Majidzadeh, K., Sangar, A. Offline writer identification using a developed deep neural network based on a novel signature dataset. Journal of Ambient Intelligence and Humanized Computing, 4(9):12425-12441, 2023.
[20] Djoudjai, M., Chibani, Y. Open writer identification from offline handwritten signatures by jointing the one-class symbolic data analysis classifier and feature-dissimilarities. International Journal on Document Analysis and Recognition, 26(1):15-31, 2023.
[21] Batool, F., Attique, M., Sharif, M., Javed, K., Nazir, M., Abbasi, A., Iqbal, Z., Riaz, N. Offline signature verification system: a novel technique of fusion of GLCM and geometric features using SVM. Multimedia Tools and Applications. 79(3): 1-20, 2020.
[22] Banerjee, D., Chatterjee, B., Bhowal, P., Bhattacharyya, T., Malakar, S., Sarkar, R. A new wrapper feature selection method for language-invariant offline signature verification. Expert Systems with Applications. 186(1):1-20, 115756, 2021.
[23] Anisimova, E., Anikin, I. Finding a rational set of features for handwritten signature recognition. In Proceedings of the International Conference on Dynamics of Systems, Mechanisms and Machines (Dynamics), pp. 1-6, 2020.
[24] Liu, J., Fung, G. Signature verification based on a fuzzy genetic algorithm. In Knowledge-Based Intelligent Techniques in Character Recognition, pp. 121-148, CRC Press, 2020.
[25] Anisimova, E., Anikin, I. Fuzzy sets theory approach for recognition handwritten signatures. In Proceedings of the International Russian Automation Conference, Sochi, Russia, pp. 969-982, Springer International Publishing, 2021.
[26] Meshram, C., Alsanad, A., Tembhurne, J., Shende, S., Kalare, K., Meshram, S., Akbar, M., Gumaei, A. A provably secure lightweight subtree-based short signature scheme with fuzzy user data sharing for human-centered IoT. IEEE Access, 9(3):3649-3659, 2020.
[27] Adeyemi, B., Olaoye, O., Uchehara, C., Akinola, O., Sunmola, F. Adoption of off-line signature verification and forgery detection system using additive fuzzy and TS modelling technique in financial auditing and forensics investigation. International Journal of Computer Science and Mobile Computing, 10(6): 38-59, 2021.
[28] Bibi K, Naz S, Rehman A. Biometric signature authentication using machine learning techniques: Current trends, challenges and opportunities. Multimedia Tools and Applications, 79(1-2):289-340. 2020.
[29] Houtinezhad, M., Ghaffary, H. Writer-independent signature verification based on feature extraction fusion. Multimedia Tools and Applications, 79(9-10):6759-6779, 2020.
[30] Makkar, G., Goyal, P. Combined static and dynamic features extraction from handwritten signature. Scandinavian Journal of Information Systems, 35(1):468-4675, 2023.
[31] Chompookham, T., Gonwirat, S., Lata, S., Phiphiphatphaisit, S., Surinta, O. Plant leaf image recognition using multiple-grid based local descriptor and dimensionality reduction approach. In Proceedings of the International Conference on Information Science and Systems, pp. 72-77, 2020.
[32] Priya, I., Chaurasia, N. Estimating the Effectiveness of CNN and Fuzzy Logic for Signature Verification. In Proceedings of the Third International Conference on Secure Cyber Computing and Communication, pp: 1-6, 2023.
[33] Yue, W., Wan, X., Li, S., Ren, H., He, H. Simplified neutrosophic petri nets used for identification of superheat degree. International Journal of Fuzzy Systems, vol. 24, no. 8, pp. 3431-3455, 2022.
[34] S. Pai, and R. Gaonkar. Safety modelling of marine systems using neutrosophic logic. Journal of Engineering for the Maritime Environment, vol. 235, pp. 225-235, 2021.
[35] Rajarao, B., Renuka, M., Sowjanya, K., Krupa, K., Babbitha, M. Offline signature verification using convolution neural network. Industrial Engineering Journal, 52(4): 1087- 1101, 2023.
