The Thermographic Face Model Appliance for Identification and Authentication
( Pp. 109-120)

The subject of this study pertains to the continued exploration of identity identification algorithms utilizing thermogram data of individuals. The novelty of this research lies in the development of a biometric thermographic model for facial recognition, capable of incorporating quasi-static points that remain unchanged over time and unaffected by external factors. Additionally, this work provides experimental confirmation of the proposed Method. Within the scope of this study, the investigated model primarily focuses on the capacity to generalize key facial areas and determine the variability weights of these areas for everyone, regardless of when the thermogram of the user’s face was captured. Furthermore, this study train algorithms that have undergone testing in previous works by the authors, as well as within the current research, forming part of the developed software and hardware complex designed to validate the concept of identifying quasi-static areas. The primary outcomes of this research reveal that the developed hardware and software complex corroborates the applicability of the algorithm based on Siamese convolutional neural networks for resolving the problem of user identification via facial thermography. This algorithm successfully competes with other biometric identification methods, including those utilizing 2D facial images. Moreover, experimental results affirm the effectiveness of isolating quasi-static regions, with an 86.41% accuracy rate in correctly identifying features identified using the developed neural network. Concerning the task of amalgamating results obtained from two identification algorithms, the stacking method based on the logistic regression algorithm emerges as the most effective. This approach yields low error rates of the first and second kinds, amounting to 6.61 and 5.63%, respectively. Furthermore, in the comparative analysis of identification algorithms based on 2D images of users’ faces, the FaceNet algorithm is deemed the most effective. This algorithm boasts high identification accuracy, even in the presence of alterations in appearance and lighting conditions. FaceNet proves especially advantageous when working with 2D facial images, significantly enhancing performance in user identification tasks based on images captured within the visible spectrum. The f-measure metric for this algorithm, trained on data from the YouTube Face DataBase, stands at 0.94. The practical significance of these research findings lies in their potential application within access control and monitoring systems to enhance the reliability of person-based authentication processes. The effective utilization of the methods presented here holds value in the realm of processing thermographic images for the purpose of identity verification, relying on the quasi-static features of the user’s facial thermogram. Such applications can be especially valuable in scenarios necessitating identification, even amidst fluctuations in facial expressions, appearance changes (such as makeup application), or variations in environmental conditions.

Belov N.I., Korzhuk V.M. The Thermographic Face Model Appliance for Identification and Authentication. Computational Nanotechnology. 2023. Vol. 10. No. 3. Pp. 109–120. (In Rus.) DOI: 10.33693/2313-223X-2023-10-3-109-120. EDN: SQVCIV

Chatterjee S., Saha D., Sen S. et al. Moth-flame optimization based deep feature selection for facial expression recognition using thermal images. Multimedia Tools and Applications. Published: 28 June 2023. DOI: https://doi.org/10.1007/s11042-023-15861-5
Paulraj B., Vasant A.R. Liveliness detection using thermograph patterns in face recognition. Mathematical Statistician and Engineering Applications. 2023. Vol. 72. No. 1. Pp. 1196–1207. DOI: 10.17762/msea.v72i1.2247
Kuzmina Y. Azovtseva A. Perminova A. Vulnerability of Biometric Protection. International Russian Smart Industry Conference (SmartIndustryCon). Sochi, Russian Federation. 2023. Pp. 275–280, DOI: 10.1109/SmartIndustryCon57312.2023.10110772
Mishra N.K., Kumar S., Singh S.K. MmLwThV framework: A masked face periocular recognition system using thermo-visible fusion. Applied Intelligence. 2023. No. 53. Pp. 2471–2487. DOI: 10.1007/s10489-022-03517-0
Belov N.I. The algorithm of biometric authentication of the user by the thermogram of the face based on the neural network architecture. Zaŝita informacii. Inside. 2023. № 2 (110). Pp. 34–37. (In Rus.)
Schroff F., Kalenichenko D., Philbin J. FaceNet: A unified embedding for face recognition and clustering. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, Pp. 815–823. URL: https://arxiv.org/abs/1503.03832 (data of accesses: 22.03.2023).
Stein G. Falconet: force-feedback approach for learning from coaching and observation using natural and experiential training: Dis. … of Dr. Sci. (Philos.). Orlando, FL. University of Central Florida, 2009. URL: https://stars.library.ucf.edu/cgi/viewcontent.cgi?article=4988&context=etd
Elistratova A.A., Kukartsev V.V. Personal identification technology DeepFace. Reshetnev readings. Vol. 2, No. 18. Pp. 186–187. (In Rus.) URL: https://cyberleninka.ru/article/n/tehnologiya-identifikatsii-lichnosti-deepface (data of accesses: 22.05.2023).
Yi Sun, Xiaogang Wang, Xiaoou Tang. Deeply learned face representations are sparse, selective, and robust. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015. Pp. 2892–2900. DOI: 10.1109/CVPR.2015.7298907. URL: https://arxiv.org/abs/1412.1265 (data of accesses: 17.03.2023).
Changxing Ding, Chang Xu, Dacheng Tao. Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018. Vol. 40. Issue 4. Pp. 1002–1014. URL: https://arxiv.org/abs/1607.05427 (data of accesses: 17.03.2023).
Skrypnikov A.V., Denisenko V.V., Demichev S.E., Samokhin A.V. Implementation of procedures of human-machine interaction. through face detection and recognition. International Journal of Humanities and Natural Sciences. 2021. Vol. 12-3 (63). Pp. 100–104. (In Rus.) URL: https://cyberleninka.ru/article/n/realizatsiya-protsedur-vzaimodeystviya-cheloveka-s-mashinoy-posredstvom-obnaruzheniya-i-raspoznavaniya-lits (data of accesses: 22.05.2023).
Katasev A.S., Kataseva D.V., Kirpichnikov А.P. Neural network biometric system for human face image recognition. Bulletin of Kazan Technological University. 2016. No. 18. (In Rus.) URL: https://cyberleninka.ru/article/n/neyrosetevaya-biometricheskaya-sistema-raspoznavaniya-izobrazheniy-chelovecheskogo-litsa (data of accesses: 22.05.2023).
Emomov M.I. Analysis of modern approaches to face recognition and matching for biometric control systems. Magistracy Bulletin. 2019. No. 1–2 (88). (In Rus.) URL: https://cyberleninka.ru/article/n/analiz-sovremennyh-podhodov-raspoznavaniya-i-sopostavleniya-lits-dlya-sistem-biometricheskogo-kontrolya (дата обращения: 22.05.2023).
Rego G.E. Face Recognition in low-quality images. SAF. 2019. No. 13. (In Rus.) URL: https://cyberleninka.ru/article/n/raspoznavanie-lits-na-izobrazheniyah-s-nizkim-kachestvom-semki (data of accesses: 22.05.2023).
Yang Li, Sangwhan Cha. Face recognition system. Computer Vision and Pattern Recognition (cs.CV). URL: https://arxiv.org/abs/1901.02452 (data of accesses: 22.05.2023).
Fares Jalled. Face recognition machine vision system using eigenfaces. Computer Vision and Pattern Recognition (cs. CV). URL: https://arxiv.org/abs/1705.02782 (data of accesses: 22.03.2023).
Martínez-Díaz Y., Vazquez H.M., López-Avila L. et al. Toward More Realistic Face Recognition Evaluation Protocols for the YouTube Faces Database. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2018. URL: https://www.researchgate.net/publication/329744028_Toward_More_Realistic_Face_Recognition_Evaluation_Protocols_for_the_YouTube_Faces_Database (data of accesses: 17.10.2022)
Belov N.I., Kuznetsov A.Yu. Methodology of dataset collecting for an authentification task based on a face thermographic image. Herald of computer and information technologies. 2022. Т. 19. No. 12 (222). Pp. 3–11. (In Rus.) URL: https://www.vkit.ru/index.php/archive-eng/1200-003-011
Zhao Wen-Yi., Chellappa R., Phillips P.J., Rosenfeld A. Face recognition: A literature survey. ACM Computing Surveys. 2003. Vol. 35. Issue 4. Pp. 399–458 URL: https://inc.ucsd.edu/mplab/users/marni/Igert/Zhao_2003.pdf
Jain A.K., Ross A., Prabhakar S. An introduction to biometric recognition. IEEE Transactions on Circuits and Systems for Video Technology. 2004. Vol. 14 (1). Pp. 4-20. URL: https://www.researchgate.net/publication/3308596_An_Introduction_to_Biometric_Recognition

quasi-static facial thermogram features, facial thermogram, facial thermogram-based identification, artificial neural networks.