احراز بی‌درنگ هویت متقاضیان خدمات الکترونیک با استفاده از روش مبتنی بر یادگیری عمیق سه بُعدی با دو مسیر

اسماعیلی, ویدا; محصل فقهی, محمود

doi:10.22052/scj.2023.246701.1086

احراز بی‌درنگ هویت متقاضیان خدمات الکترونیک با استفاده از روش مبتنی بر یادگیری عمیق سه بُعدی با دو مسیر

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده مهندسی برق و کامپیوتر، دانشگاه تبریز، تبریز، ایران

10.22052/scj.2023.246701.1086

چکیده

احراز هویت در فضای مجازی، حفظ امنیت را به دنبال دارد و اگر با دقت بسیار بالا انجام شود، می‌تواند برای تداوم خدمت‌رسانی در شرایط مختلف مورد توجه قرار گیرد. پژوهش حاضر با هدف پیشنهاد یک روشی کاربردی برای احراز هویت متقاضیان خدمات الکترونیک به صورت بی‌درنگ ارائه شده است. برای جلوگیری از حقه‌های احتمالی کاربران، در روش پیشنهادی از شناسایی حرکات ماهیچه‌های صورت و سنجه بیومتریکی عنبیه استفاده شده است. عنبیه قابلیت اطمینان بیشتری را ایجاد می‌کند و قابل سرقت و جعل نیست؛ زیرا باید به صورت زنده در اختیار باشد. برای احراز هویت و به طور همزمان، شناسایی حرکات ماهیچه‌های صورت و تمییز فرد زنده از تصویر، یک روش مبتنی بر یادگیری عمیق سه بُعدی با دو مسیر پیشنهاد شده است. با توجه به ارزیابی‌ها مشخص شد که روش پیشنهادی اطمینان قابل توجهی را برای استفاده عموم فراهم می‌آورد و قابل اجرا در شرایط واقعی و عملی می‌باشد. با استفاده از روش پیشنهادی، دقت 99.99 درصد و میانگین صحت احراز هویت و شناسایی افراد در هر دو پایگاه داده CASME و CASME2 بیش از 99.50 درصد است.

کلیدواژه‌ها

عنوان مقاله [English]

Real-time Authentication for Electronic Service Applicants using a Method Based on Two-Stream 3D Deep Learning

نویسندگان [English]

Vida Esmaeili
Mahmood Mohassel Feghhi

Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran

چکیده [English]

Authentication in cyberspace aims to maintain security, and if it is done with high accuracy, it can be considered for the continuity of service delivery under different conditions. The present research aims to propose a fully applicable method for authentication of the applicants for electronic services in real time. In order to prevent the possible tricks of the users, in the proposed method, the identification of facial muscle movements and iris biometric measurement have been used. The iris creates more reliability and cannot be stolen or faked; because it must be available live. A method based on two-stream 3D deep learning is proposed for authentication and simultaneously identifying facial muscle movements and distinguishing a living person from an image. According to the evaluations, it was found that the proposed method provides significant assurance for public use and is applicable in real and practical conditions. Using the proposed method, the accuracy is 99.99%, and the average precision of authentication and identifying people in both CASME and CASME2 databases is more than 99.5%.

کلیدواژه‌ها [English]

Authentication
Iris biometrics
Detection of facial muscle movements
Deep learning
Two-Stream 3D-DenseNet

مراجع

[1] R. Saniei, A. Qeble, and M. Ebrahimi Moghadam, “identity recognition based on the way of walking using fuzzy-spiky hierarchical model,” Comput. Sci. J., vol. 3, no. 4, pp. 80-95, 2018 [In Persian].
[2] V. Esmaeili, M. Mohassel Feghhi, and S.O. Shahdi, “A comprehensive survey on facial micro-expression: approaches and databases,” Multim. Tools Appl., vol. 81, no. 28, pp. 40089-40134, 2022, doi: 10.1007/s11042-022-13133-2.
[3] V. Esmaeili and M. Mohassel Feghhi, “Diagnosis of Covid-19 Disease by Combining Hand-crafted and Deep-learning Methods on Ultrasound Data,” J. Mach. Vis. Image Process., vol. 9, no. 4, pp. 31-41, 2022, dor: 20.1001.1.23831197.1401.9.4.3.0.
[4] V. Esmaeili, M. Mohassel Feghhi, and S.O. Shahdi, “Early COVID-19 Diagnosis from Lung Ultrasound Images Combining RIULBP-TP and 3D-DenseNet,” in 9th Iranian Joint Congress on Fuzzy and Intelligent Systems (CFIS), Bam, Iran, 2022, pp. 1-5, doi: 10.1109/CFIS54774.2022.9756430.
[5] M. Eftekharian and A. Nodehi, “Breast Cancer Diagnosis and Classification Improvement based on Deep Learning and image Processing methods,” Soft Comput. J., 2022, doi: 10.22052/scj.2023.246416.1067 [In Persian].
[6] F. Zare Mehrjardi, M. Yazdian-Dehkordi, and A. Latif, “Evaluating classical machine learning and deep-learning methods in sentiment analysis of Persian telegram message,” Soft Comput. J., vol. 11, no. 1, pp. 88-105, 2022, doi: 10.22052/scj.2023.246553.1077 [In Persian].
[7] Z. Farahmandpoor, H. Nikmehr, M. Mansoorizade, and O. Tabibzadeh Ghamsary, “A Novel Intelligent Persian Authorship System based on Writing Style,” Soft Comput. J., vol. 1, no. 2, pp. 26-35, 2013, dor: 20.1001.1.23223707.1391.1.2.60.9 [In Persian].
[8] J. Daugman, “How iris recognition works,” IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 1, pp. 21-30, 2004, doi: 10.1109/TCSVT.2003.818350.
[9] T.W. Ng, T.L. Tay, and S.W. Khor, “Iris recognition using rapid Haar wavelet decomposition,” in 2nd Int. Conf. Signal Process. Syst., Dalian, China, 2010, pp. V1-820-V1-823, doi: 10.1109/ICSPS.2010.5555246.
[10] L. Ma, Y. Wang, and T. Tan, “Iris recognition using circular symmetric filters,” in Proc. 16th Int. Conf. Pattern Recognit., Quebec City, QC, Canada, 2002, pp. 414-417 vol.2, doi: 10.1109/ICPR.2002.1048327.
[11] C.-H. Park, J.-J. Lee, M.J. Smith, and K.-H. Park, “Iris based personal authentication using a normalized directional energy feature,” in Proc. Int. Conf. Audio Video-Based Biometric Person Authentication, Berlin, Heidelberg, doi: 10.1007/3-540-44887-X_27.
[12] A. Czajka, D. Moreira, K.W. Bowyer, and P.J. Flynn, “Domain-specific human-inspired binarized statistical image features for Iris recognition,” in Proc. IEEE Winter Conf. Appl. Comput. Vis. (WACV), Waikoloa, HI, USA, 2019, pp. 959-967, doi: 10.1109/WACV.2019.00107.
[13] N. Liu, M. Zhang, H. Li, Z. Sun, and T. Tan, “Deepiris: Learning pairwise filter bank for heterogeneous iris verification,” Pattern Recognit. Lett., vol. 82, pp. 154-161, 2016, doi: 10.1016/j.patrec.2015.09.016.
[14] A. Gangwar and A. Joshi, “DeepIrisNet: Deep iris representation with applications in iris recognition and cross sensor iris recognition,” in Proc. IEEE Int. Conf. Image Process. (ICIP), Phoenix, AZ, USA, 2016, pp. 2301-2305, doi: 10.1109/ICIP.2016.7532769.
[15] Z. Zhao and A. Kumar, “Towards more accurate iris recognition using deeply learned spatially corresponding features,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Venice, Italy, 2017, pp. 3829-3838, doi: 10.1109/ICCV.2017.411.
[16] K. Wang and A. Kumar, “Toward more accurate iris recognition using dilated residual features,” IEEE Trans. Inf. Forensics Security, vol. 14, no. 12, pp. 3233-3245, 2019, doi: 10.1109/TIFS.2019.2913234.
[17] K. Nguyen, C. Fookes, A. Ross, and S. Sridharan, “Iris recognition with off-the-shelf CNN features: A deep learning perspective,” IEEE Access, vol. 6, pp. 18848-18855, 2018, doi: 10.1109/ACCESS.2017.2784352.
[18] S. Minaee, A. Abdolrashidiy, and Y. Wang, “An experimental study of deep convolutional features for iris recognition,” in Proc. IEEE Signal Process. Med. Biol. Symp. (SPMB), Philadelphia, PA, USA, 2016, pp. 1-6, doi: 10.1109/SPMB.2016.7846859.
[19] T. Zhao, Y. Liu, G. Huo, and X. Zhu, “A deep learning iris recognition method based on capsule network architecture,” IEEE Access, vol. 7, pp. 49691-49701, 2019, doi: 10.1109/ACCESS.2019.2911056.
[20] J.E. Zambrano, D.P. Benalcazar, C.A. Perez, and K.W. Bowyer, “Iris Recognition Using Low-Level CNN Layers Without Training and Single Matching,” IEEE Access, vol. 10, pp. 41276-41286, 2022, doi: 10.1109/ACCESS.2022.3166910.
[21] J. Sun, S. Zhao, S. Miao, X. Wang, and Y. Yu, “Open?set iris recognition based on deep learning,” IET Image Process., vol. 16, no. 9, pp. 2361-2372, 2022, doi: 10.1049/ipr2.12493.‏
[22] M.R.R. Fini, M.A.A. Kashani, and M. Rahmati, “Eye detection and tracking in image with complex background,” in 3rd Int. Conf. Electron. Comput. Technol., Kanyakumari, India, 2011, pp. 57-61, doi: 10.1109/ICECTECH.2011.5942050.
[23] M.A.A. Kashani, M.M. Arani, and M.R.R. Fini, “Eye detection and tracking in images with using bag of pixels,” in 3rd Int. Conf. Commun. Softw. Networks, Xi’an, China, 2011, pp. 64-68, doi: 10.1109/ICCSN.2011.6014219.
[24] C. Tomasi and T. Kanade, Detection and Tracking of Point Features, School of Computer Science, Carnegie Mellon Univ. Pittsburgh, 1991.
[25] X. Li, X. Hong, A. Moilanen, X. Huang, T. Pfister, G. Zhao, and M. Pietikainen, “Towards reading hidden emotions: a comparative study of spontaneous micro-expression spotting and recognition methods,” IEEE Trans. Affect. Comput., vol. 9, no. 4, pp. 563–577, 2018, doi: 10.1109/TAFFC.2017.2667642.
[26] C. Hu, D. Jiang, H. Zou, X. Zuo, and Y. Shu, “Multi-task micro-expression recognition combining deep and handcrafted features,” in 24th Int. Conf. Pattern Recogni. (ICPR), Beijing, China, 2018, pp. 946-951, doi: 10.1109/ICPR.2018.8545555.
[27] W.J. Yan, X. Li, S.J. Wang, G. Zhao, Y.J. Liu, Y.H. Chen, and X. Fu, X., “CASME II: An improved spontaneous micro-expression database and the baseline evaluation,” PloS one, vol. 9, no. 1, p. e86041, 2014, doi: 10.1371/journal.pone.0086041.
[28] W.J. Yan, Q. Wu, Y.J. Liu, S.J. Wang, and X. Fu, “CASME database: a dataset of spontaneous micro-expressions collected from neutralized faces,” in 10th IEEE Int. Conf. Worksh. Autom. Face Gesture Recogni. (FG), Shanghai, China, 2013, pp. 1-7, doi: 10.1109/FG.2013.6553799.
[29] H. Dalianis, “Evaluation Metrics and Evaluation,” in Clinical Text Mining, pp.45-53, 2018, doi: 10.1007/978-3-319-78503-5_6.
[30] V. Esmaeili, M. Mohassel Feghhi, S.O. Shahdi, “Spotting micro?movements in image sequence by introducing intelligent cubic?LBP,” IET Image Process., vol. 16, no. 14, pp. 3814-3830, 2022, doi: 10.1049/ipr2.12596.
[31] V. Esmaeili, M. Mohassel Feghhi, S.O. Shahdi, “Automatic Micro-Expression Recognition using LBP-SIPl and FR-CNN,” AUT J. Model. Simul., vol. 54, no. 1, pp. 59-72, 2022, doi: 10.22060/MISCJ.2022.21133.5272.
[32] V. Esmaeili, M. Mohassel Feghhi, S.O. Shahdi, “Micro-Expression Recognition based on the Multi-Color ULBP and Histogram of Gradient Direction from Six Intersection Planes,” J. Iranian Assoc. Electr. Electron. Eng., vol. 19, no. 3, pp. 123-130, 2022, doi: 10.52547/jiaeee.19.3.123.