Effectiveness and limitations of biometric systems in identity verification: A systematic review

• Autores: Bocanegra Chistama, Bruno Samir, Fernández Salvo, Fernando Arturo, Mendoza De Los Santos, Alberto Carlos
• Formato: artículo
• Fecha de Publicación: 2024
• Institución: Universidad Privada de Tacna
• Repositorio: Revistas - Universidad Privada de Tacna
• Lenguaje: español
• OAI Identifier: oai:revistas.upt.edu.pe:article/1099
• Enlace del recurso: https://revistas.upt.edu.pe/ojs/index.php/ingenieria/article/view/1099
• Nivel de acceso: acceso abierto
• Materia: control de acceso; sistemas de seguridad; inteligencia artificial; biometría; access control; security systems; artificial intelligence; biometrics

Increasing digitization and automation demand advanced and secure methods for access control. This study synthesized artificial intelligence (AI) tools applied in this field, through a literature review in databases such as Scopus, SciELO and IEEE Xplore, using PRISMA and VOSviewer. The bibliometric analysis identified China, India, the United States and South Korea as leaders in research, highlighting terms such as machine learning, deep learning, cryptography and biometrics, along with emerging technologies such as blockchain and IoT. Machine learning and deep learning stood out as predominant techniques, while blockchain brought transparency in the management of sensitive data. However, challenges such as high costs, reliance on big data and privacy concerns limit its implementation. It is recommended to explore hybrid methods, optimize AI models and reduce data dependency to improve security and adoption of these technologies.