Facial recognition system with and without face mask using Haar cascade, LBPH, Eigenface and Fisherface classifiers
Facial recognition system with facemask using Haar cascade, LBPH, Eigenface and Fisherface classifiers
DOI:
https://doi.org/10.33131/24222208.386Keywords:
classification algorithm, expert training system, artificial intelligence, image processingAbstract
The implementation of automated access systems in high-traffic areas, such as transportation systems and healthcare centers, is a growing necessity to mitigate congestion and work-related stress. In this context, facial recognition emerges as an effective solution, offering personalized and efficient access control. Artificial intelligence, combined with robust databases, enables precise facial identification, and when complemented with face classifiers, facilitates facial recognition. The Haar Cascade classifier operates through small classifiers that analyze different portions of a facial image, which are then combined to provide a precise detection result, facilitating the creation of a database that can be trained by recognition algorithms. This study presents a facial recognition system using the Haar Cascade classifier for image collection, and the Local Binary Patterns Histogram (LBPH), EigenFace (EF), and FisherFace (FF) classifiers for the recognition process. The data collection included images of six individuals, obtaining 350 images without face masks and 350 images with face masks. Training times varied between 9.54 seconds and 9287.64 seconds. Once the models were trained, the facial recognition time ranged from 0.0001 seconds to 0.4447 seconds. The recognition accuracy with the LBPH classifier ranged from 80.9069% to 100%, with the EF classifier from 69.7542% to 100%, and with the FF classifier from 31.6017% to 91.3684%. These results demonstrate the speed of the proposed facial recognition system, highlighting the accuracy and speed of the LBPH classifier.
Downloads
References
S. O. Adeshina, H. Ibrahim, S. S. Teoh, y S. C. Hoo, «Custom Face Classification Model for Classroom Using Haar-Like and LBP Features with Their Performance Comparisons», Electronics, vol. 10, n.o 2, p. 102, ene. 2021, doi: https://doi.org/10.3390/electronics10020102
P. A. Riyantoko, Sugiarto, y K. M. Hindrayani, «Facial Emotion Detection Using Haar-Cascade Classifier and Convolutional Neural Networks», J. Phys. Conf. Ser., vol. 1844, n.o 1, p. 012004, mar. 2021, doi: https://doi.org/10.1088/1742-6596/1844/1/012004.
C. A. Amaya Corredor, C. H. Contreras, N. Pedroza Rosas, y R. S. Cáceres Quintero, «Estrategias de adaptación y mitigación al cambio climático de las Unidades Tecnológicas de Santander», Rev. CINTEX, vol. 22, n.o 2, pp. 89-109, dic. 2017, doi: https://doi.org/10.33131/24222208.301.
A. Uribe Churta, «Desarrollo de un sistema de reconocimiento del estado de los cultivos de café en tiempo real usando redes neuronales artificiales», Rev. CINTEX, vol. 25, n.o 2, pp. 37-44, dic. 2020, doi: https://doi.org/10.33131/24222208.362.
M. Turk y A. Pentland, «Eigenfaces for Recognition», J. Cogn. Neurosci., vol. 3, n.o 1, pp. 71-86, ene. 1991, doi: https://doi.org/10.1162/jocn.1991.3.1.71.
B. Moghaddam y A. Pentland, «Probabilistic visual learning for object representation», IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, n.o 7, pp. 696-710, jul. 1997, doi: https://doi.org/10.1109/34.598227.
E. Osuna, R. Freund, y F. Girosit, «Training support vector machines: an application to face detection», en Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, 1997, pp. 130-136. doi: https://doi.org/10.1109/CVPR.1997.609310.
M.-H. Yang, D. Roth, y N. Ahuja, «A SNoW-Based Face Detector», en Advances in Neural Information Processing Systems, 1999, vol. 12. [En línea]. Disponible en: https://proceedings.neurips.cc/paper/1999/file/3e15cc11f979ed25912dff5b0669f2cd-Paper.pdf
P. Viola y M. Jones, «Rapid object detection using a boosted cascade of simple features», en Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, Kauai, HI, USA, 2001, vol. 1, p. I-511-I-518. doi: https://doi.org/10.1109/CVPR.2001.990517.
P. Viola y M. J. Jones, «Robust Real-Time Face Detection», Int. J. Comput. Vis., vol. 57, n.o 2, pp. 137-154, may 2004, doi: https://doi.org/10.1023/B:VISI.0000013087.49260.fb.
T. F. Cootes, K. Walker, y C. J. Taylor, «View-based active appearance models», en Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580), Grenoble, France, 2000, pp. 227-232. doi: https://doi.org/10.1109/AFGR.2000.840639.
Q. Yin, X. Tang, y J. Sun, «An associate-predict model for face recognition», en CVPR 2011, Colorado Springs, CO, USA, jun. 2011, pp. 497-504. doi: https://doi.org/10.1109/CVPR.2011.5995494.
V. Blanz y T. Vetter, «A morphable model for the synthesis of 3D faces», en Proceedings of the 26th annual conference on Computer graphics and interactive techniques - SIGGRAPH ’99, Not Known, 1999, pp. 187-194. doi: https://doi.org/10.1145/311535.311556.
K.-K. Sung y T. Poggio, «Example-based learning for view-based human face detection», IEEE Trans. Pattern Anal. Mach. Intell., vol. 20, n.o 1, pp. 39-51, ene. 1998, doi: https://doi.org/10.1109/34.655648.
A. B. Shetty, Bhoomika, Deeksha, J. Rebeiro, y Ramyashree, «Facial recognition using Haar cascade and LBP classifiers», Glob. Transit. Proc., vol. 2, n.o 2, pp. 330-335, nov. 2021, doi: 10.1016/j.gltp.2021.08.044.
S. Pal, «Human Face Detection Technique using Haar-like Features», Int. J. Comput. Appl., vol. 175, n.o 32, pp. 56-60, nov. 2020, doi: https://doi.org/10.5120/ijca2020920883.
I. Gangopadhyay, A. Chatterjee, y I. Das, «Face Detection and Expression Recognition Using Haar Cascade Classifier and Fisherface Algorithm», en Recent Trends in Signal and Image Processing, vol. 922, S. Bhattacharyya, S. K. Pal, I. Pan, y A. Das, Eds. Singapore: Springer Singapore, 2019, pp. 1-11. doi: https://doi.org/10.1007/978-981-13-6783-0_1.
F. M. Javed Mehedi Shamrat, A. Majumder, P. R. Antu, S. K. Barmon, I. Nowrin, y R. Ranjan, «Human Face Recognition Applying Haar Cascade Classifier», en Pervasive Computing and Social Networking, vol. 317, G. Ranganathan, R. Bestak, R. Palanisamy, y Á. Rocha, Eds. Singapore: Springer Nature Singapore, 2022, pp. 143-157. doi: https://doi.org/10.1007/978-981-16-5640-8_12.
A. H. Ahmad et al., «Real time face recognition of video surveillance system using haar cascade classifier», Indones. J. Electr. Eng. Comput. Sci., vol. 21, n.o 3, p. 1389, mar. 2021, doi: https://doi.org/10.11591/ijeecs.v21.i3.pp1389-1399.
J. J. Castro-Maldonado, J. A. Patiño-Murillo, A. E. Florian-Villa, y O. E. Guadrón-Guerrero, «Application of computer vision and low-cost artificial intelligence for the identification of phytopathogenic factors in the agro-industry sector», J. Phys. Conf. Ser., vol. 1126, p. 012022, nov. 2018, doi: https://doi.org/10.1088/1742-6596/1126/1/012022.
Z. Abal Abas et al., «The implementation of personal monitoring system using Histogram of Gradient, Haar classifier and eigenfaces for human detection and recognition», ARPN J Eng Appl Sci, vol. 10, n.o 19, pp. 8799-8806, 2015.
B. G. Amira, M. M. Zoulikha, y P. Hector, «Driver Drowsiness Detection and Tracking Based on Yolo with Haar Cascades and ERNN», Int. J. Saf. Secur. Eng., vol. 11, n.o 1, pp. 35-42, feb. 2021, doi: https://doi.org/10.18280/ijsse.110104.
N. Kamarudin et al., «Implementation of Haar Cascade Classifier and Eye Aspect Ratio for Driver Drowsiness Detection Using Raspberry Pi», Univers. J. Electr. Electron. Eng., vol. 6, n.o 5B, pp. 67-75, dic. 2019, doi: https://doi.org/10.13189/ujeee.2019.061609.
C. Adarve Gómez, D. A. Castillo Carvajal, E. J. Restrepo Zapata, y H. Villar-Vega, «A review of virtual reality videogames for job-training applications», Rev. CINTEX, vol. 24, n.o 1, pp. 64-70, dic. 2019, doi: https://doi.org/10.33131/24222208.346.
R. Rizal Isnanto, A. Rochim, D. Eridani, y G. Cahyono, «Multi-Object Face Recognition Using Local Binary Pattern Histogram and Haar Cascade Classifier on Low-Resolution Images», Int. J. Eng. Technol. Innov., vol. 11, n.o 1, pp. 45-58, ene. 2021, doi: https://doi.org/10.46604/ijeti.2021.6174.
V. Ravuri, S. Vasundra, S. Ramasubbareddy, y K. Govinda, «Face Recognition using Cascade Algorithm», Int. J. Recent Technol. Eng., vol. 8, n.o 2S4, pp. 599-602, ago. 2019, doi: https://doi.org/10.35940/ijrte.B1118.0782S419.
School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India, R. Shukla*, A. L, School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India, P. M, y School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India, «Facial Emotion Recognition by Deep CNN and HAAR Cascade», Int. J. Innov. Technol. Explor. Eng., vol. 8, n.o 12, pp. 3433-3439, oct. 2019, doi: https://doi.org/10.35940/ijitee.L2589.1081219.
M. Maria Dominic Savio, T. Deepa, A. Bonasu, y T. S. Anurag, «Image Processing For Face Recognition Using HAAR, HOG, and SVM Algorithms», J. Phys. Conf. Ser., vol. 1964, n.o 6, p. 062023, jul. 2021, doi: https://doi.org/10.1088/1742-6596/1964/6/062023.
N. Ibrahim, «Haar Cascade Vs Facial Landmarks Technique for Face Recognition Uniqueness», Int. J. Adv. Trends Comput. Sci. Eng., vol. 8, n.o 1.6, pp. 525-530, dic. 2019, doi: https://doi.org/10.30534/ijatcse/2019/7781.62019.
F. Utaminingrum, Y. A. Sari, P. P. Adikara, D. Syauqy, y S. Adinugroho, «Hybrid Head Tracking for Wheelchair Control Using Haar Cascade Classifier and KCF Tracker», TELKOMNIKA Telecommun. Comput. Electron. Control, vol. 16, n.o 4, p. 1616, feb. 2018, doi: https://doi.org/10.12928/telkomnika.v16i4.6595.
R. Raj et al., «Feature based video stabilization based on boosted HAAR Cascade and representative point matching algorithm», Image Vis. Comput., vol. 101, p. 103957, sep. 2020, doi: https://doi.org/10.1016/j.imavis.2020.103957.
M. M. Ahsan, Y. Li, J. Zhang, M. T. Ahad, y K. D. Gupta, «Evaluating the Performance of Eigenface, Fisherface, and Local Binary Pattern Histogram-Based Facial Recognition Methods under Various Weather Conditions», Technologies, vol. 9, n.o 2, p. 31, abr. 2021, doi: https://doi.org/10.3390/technologies9020031.
A. M. Jagtap, V. Kangale, K. Unune, y P. Gosavi, «A Study of LBPH, Eigenface, Fisherface and Haar-like features for Face recognition using OpenCV», en 2019 International Conference on Intelligent Sustainable Systems (ICISS), Palladam, Tamilnadu, India, feb. 2019, pp. 219-224. doi: https://doi.org/10.1109/ISS1.2019.8907965.
D. Verdeguer Valderrama y N. Campos Vasquez, «Diseño E Implementación De Un Sistema De Identificación De Personas Para La Seguridad De Los Accesos A Condominios, Basado En El Algoritmo De Reconocimiento Facial LBPH Faces», en Proceedings of the 19th LACCEI International Multi-Conference for Engineering, Education, and Technology: “Prospective and trends in technology and skills for sustainable social development” “Leveraging emerging technologies to construct the future”, 2021. doi: https://doi.org/10.18687/LACCEI2021.1.1.213.
J. Paul et al., «Evaluation of Face Recognition Schemes for Low-computation IoT System Design», en 2020 24th International Symposium on VLSI Design and Test (VDAT), Bhubaneswar, India, jul. 2020, pp. 1-6. doi: https://doi.org/10.1109/VDAT50263.2020.9190569.
M. Munlin, «Time Attendance Using FELE Face Identification Algorithms», en 2022 9th International Conference on Electrical and Electronics Engineering (ICEEE), Alanya, Turkey, mar. 2022, pp. 325-329. doi: https://doi.org/10.1109/ICEEE55327.2022.9772596.
C. H. Esparza Franco, C. Tarazona Ospina, E. E. Sanabria Cuevas, y D. A. Velazco Capacho, «RECONOCIMIENTO FACIAL BASADO EN EIGENFACES, LBHP Y FISHERFACES EN LA BEAGLEBOARD-xM», Rev. Colomb. Tecnol. Av. RCTA, vol. 2, n.o 26, pp. 145-152, ene. 2021, doi: https://doi.org/10.24054/16927257.v26.n26.2015.395.
C. A. Ramírez Gómez, «Aplicación del Machine Learning en agricultura de precisión», Rev. CINTEX, vol. 25, n.o 2, pp. 14-27, dic. 2020, doi: https://doi.org/10.33131/24222208.356.
M. üge Çarıkçı y F. Özen, «A Face Recognition System Based on Eigenfaces Method», Procedia Technol., vol. 1, pp. 118-123, 2012, doi: https://doi.org/10.1016/j.protcy.2012.02.023.
I. Markoulidakis, I. Rallis, I. Georgoulas, G. Kopsiaftis, A. Doulamis, y N. Doulamis, «Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem», Technologies, vol. 9, n.o 4, p. 81, nov. 2021, doi: https://doi.org/10.3390/technologies9040081.
A. Kulkarni, D. Chong, y F. A. Batarseh, «Foundations of data imbalance and solutions for a data democracy», en Data Democracy, Elsevier, 2020, pp. 83-106. doi: https://doi.org/10.1016/B978-0-12-818366-3.00005-8.
Downloads
Published
How to Cite
Issue
Section
