Optimization and implementation of a system recognition of faces

• Autores: del Carpio Salinas, Jorge Alberto, Huamán Layme, Jose Antonio
• Formato: artículo
• Fecha de Publicación: 2006
• Institución: Universidad Nacional de Ingeniería
• Repositorio: Revistas - Universidad Nacional de Ingeniería
• Lenguaje: español
• OAI Identifier: oai:oai:revistas.uni.edu.pe:article/387
• Enlace del recurso: https://revistas.uni.edu.pe/index.php/tecnia/article/view/387
• Nivel de acceso: acceso abierto
• Materia: base de datos; biometría; cámara; sensores; eigenfaces; métodos estadísticos; modelo de markov; statistical data base; biometry; camera; sensors; statistical methods; model of markov

Security systems controlled by biometric type characteristics are experiencing a growing interest compared to traditional alternatives. This success is largely due to the fact that, when a person wants to access a system, the decision is made based on specific characteristics of that person, and not based on what is known or what he or she has (magnetic cards, passwords, etc.). , etc); In recent years, the great development of information systems, together with the spread and massification of computers and sensors, has led to a growing interest in systems that allow the identity of an individual to be established in an automated manner. Faced with this, this work describes and implements a face recognizer using the most successful techniques in the field of biometrics based on Statistical methods such as: Eingenface type decompositions and Embedded Hidden Markov Model (HMME). The first method generates a reduced linear representation of the face images so that each face is projected in a reduced dimensional space where recognition will take place. The second method generates a model of states. For this, a database of faces obtained with students from the National University of Engineering UNI, a camera, a digitizing card has been used and the system was implemented almost in real time using C++.