Entrenamiento de un modelo para reconocimiento facial aplicado a un sistema de préstamo de equipo

Francisco Gibrán García Candelario; Natividad Juárez González; José Aurelio Ramírez González; Wendy Carranza Díaz

doi:10.61117/ipsumtec.v4i3.71

Authors

Francisco Gibrán García Candelario Tecnológico Nacional de México https://orcid.org/0000-0002-8253-9450
Natividad Juárez González Tecnológico Nacional de México https://orcid.org/0000-0001-8054-8604
José Aurelio Ramírez González Tecnológico Nacional de México https://orcid.org/0000-0002-5986-4837
Wendy Carranza Díaz Tecnológico Nacional de México https://orcid.org/0000-0003-3415-1141

DOI:

https://doi.org/10.61117/ipsumtec.v4i3.71

Keywords:

Face recognition, LBPH, API, OpenCV

Abstract

Facial recognition opens an alternative to computer systems that require user authentication, allowing applications in information security, smartcards, and access control. Currently, some services perform facial recognition with a monetary charge. In this article, we show the training of an artificial vision model to locally perform facial recognition of users requesting equipment loan, avoiding the monetary charges that other applications request.AnAPI was developed to use the trained model by applying the LBPH algorithm through the open source library OpenCV to determine if a face is found in the valid face set. The API is used in a web application that records the equipment loan for the Tecnológico Nacional de México campus Acayucan.

It was possible to obtain an F1-Score accuracy of 90% without relying on any proprietary or payment technology with a prediction time of less than 100 milliseconds per query.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

References

Aguillón, M. (2020). Sistema para la detección de dolor por medio de expresiones faciales. [Tesis de Maestría]. CICESE, Baja California, México. Recuperado de: https://cicese.repositorioinstitucional.mx/jspui/bitstream/1007/3222/1/Tesis_Mar%C3%ADa%20Lourdes_Aguillon%20Ruiz_13_feb_2020.pdf

Colmenarez, A. J. & Huang, T. S. (1998). Face detection and recognition. In Face Recognition (pp. 174-185). Springer, Berlin, Heidelberg. DOI: https://doi.org/10.1007/978-3-642-72201-1_9

Deeba, F., Ahmed, A., Memon, H., Dharejo, F. A., & Ghaffar, A. (2019). LBPH-based enhanced real-time fase recognition. Int J Adv Comput Sci Appl,10(5), 274-280. DOI: https://doi.org/10.14569/IJACSA.2019.0100535

Fielding, R. T. (2000). Architectural styles and the design of network-based software architectures.

Kumar, A., Kaur, A., & Kumar, M. (2019). Face detection techniques: a review. Artificial Intelligence Review, 52(2), 927-948. DOI: https://doi.org/10.1007/s10462-018-9650-2

Kumar, S. & Walia, E. (2011). Analysis of various biometric techniques. International Journal of Computer Science and Information Technologies, 2(4),1595-1597.

Llapapasca, M. M. Creación de una librería de software de reconocimiento facial enfocado a la identificación de trabajadores de una empresa. Universidad Tecnológica de Lima Perú

Masek, P., & Thulin, M. (2015). Evaluation of face recognition apis and libraries.

Masupha, L., Zuva, T., Ngwira, S., & Esan, O. (2015). Face recognition techniques, their advantages, disadvantages and performance evaluation. In 2015 International Conference on Computing, Communication and Security (ICCCS) (pp. 1-5). IEEE. DOI: https://doi.org/10.1109/CCCS.2015.7374154

Powers, D. M. (2020). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061.

Raza, M., Iqbal, M., Sharif, M., & Haider, W. (2012). A survey of password attacks and comparative análisis on methods for secure authentication. World Applied Sciences Journal,19(4), 439-444.

Shetty, A. B., & Rebeiro, J. (2021). Facial Recognition using Haar Cascade and LBP Classifiers. Global Transitions Proceedings. DOI: https://doi.org/10.1016/j.gltp.2021.08.044

Tistarelli, M. & Grosso, E. (2010). Human Face Analysis: From Identity to Emotion and Intention Recognition. In International Conference on Ethics and Policy of Biometrics (pp. 76-88). Springer, Berlin, Heidelberg. DOI: https://doi.org/10.1007/978-3-642-12595-9_11

University of California, Irvine. Oliphant, T. E. (2007). Python for scientific computing. Computing in science & engineering, 9(3), 10-20. DOI: https://doi.org/10.1109/MCSE.2007.58

Zhang, B., Gao, Y., Zhao, S., & Liu, J. (2009). Local derivative pattern versus local binary pattern: fase recognition with high-order local pattern descriptor. IEEE transactions on image processing,19(2), 533-544. DOI: https://doi.org/10.1109/TIP.2009.2035882

Zhang, C., & Zhang, Z. (2010). A survey of recent advances in fase detection.