Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Recolector de Ciencia Abierta, RECOLECTA
Bachelor thesis . 2017
License: CC BY NC ND
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
versions View all 2 versions
addClaim

Reconocimiento facial mediante el Análisis de Componentes Principales (PCA)

Authors: Domínguez Pavón, Sara;

Reconocimiento facial mediante el Análisis de Componentes Principales (PCA)

Abstract

Los sistemas de reconocimiento facial han recibido un fuerte impulso en la actualidad gracias al avance en la tecnología. Dado que este tipo de técnicas tienen muchas aplicaciones útiles en campos muy diversos como la biometría, la clasificación de imágenes o la seguridad, se han destinado muchos esfuerzos tanto económicos como científicos para tratar de mejorarlas. El proceso de reconocimiento facial se divide en dos tareas. La primera de ellas, la detección, comprende la localización de una o varias caras dentro de una imagen, ya sea una imagen fija o una secuencia de video. La segunda tarea, el reconocimiento, consiste en la comparación de la cara detectada con anterioridad con otras almacenadas previamente en una base de datos. Estos dos procesos no deben ser totalmente independientes, ya que un buen reconocimiento depende fuertemente de la previa detección, la cual está condicionada por la posición y orientación de la cara del sujeto con respecto a la cámara y las condiciones de iluminación. En este trabajo se estudia, implementa y evalúa un sistema automático de reconocimiento facial, tanto para trabajar con imágenes como con videos, además de en tiempo real. Como punto de partida se realizará un estudio de las técnicas de reconocimiento facial ya existentes en el estado del arte. Tras ese primer análisis, se seleccionará una de las técnicas analizadas para su posterior implementación en Python en un sistema capaz de detectar y reconocer rostros de personas introducidas previamente en el sistema en la fase de entrenamiento. En este caso, se implementará el método Eigenfaces, construido sobre técnicas de Análisis deComponentes Principales (PCA). Finalmente, se harán un conjunto de pruebas sobre diferentes bases de datos de imágenes para analizar y verificar los resultados obtenidos tras aplicar el algoritmo implementado.

Facial recognition systems have received a strong boost at presents thanks to advances in technology. All these techniques have many useful applications and can be applied in many different areas such as biometrics, image classification or security. That’s the reason why society has invested a lot of economic and investigation efforts in improving them. Facial recognition process is divided into two tasks. The first of these, detection, comprises the location of one or more faces within an image or a video sequence. The second task, recognition, consists of the comparison of the previously detected face with others previously saved in a database. These two processes should not be totally independent, since a good recognition depends strongly on the previous detection, which is conditioned by the position and orientation of the face of the subject in respect to the camera and the lighting conditions. In this project, an automatic real time face recognition system is studied, implemented and evaluated, both to work with images and with videos. First of all, a study of facial recognition techniques in the state of the art will be carried out. Once we will have finished this first analysis, we will choose one of the analysed techniques in order to develop them. We will develop in Python a system able to detect and recognize faces from people who have been entered on the system previously in a training phase. In this case, the Eigenfaces method built over techniques of Principal Component Analysis (PCA), will be implemented. Finally, we will make some tests on different image databases to analyse and check the results got from using the algorithms developed.

Universidad de Sevilla. Grado en Ingeniería de las Tecnologías de Telecomunicación

Country
Spain
Related Organizations
Keywords

PCA, Reconocimiento facial

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green