Titre :	Face recognition using Deep Learning
Type de document :	texte manuscrit
Auteurs :	Ibrahim Chorana, Auteur ; Younes Guellouma, Directeur de thèse
Editeur :	Laghouat : Université Amar Telidji - Département d'informatique
Année de publication :	2018
Importance :	60 p.
Format :	30 cm.
Accompagnement :	1 disque optique numérique (CD-ROM)
Note générale :	Option : (Decision-making information systems) Systèmes d'information et de décision
Langues :	Anglais
Mots-clés :	Machine Learning  Deep Learning  CNNS  Face Recognition  Facial hair Recognition
Résumé :	Nowdays, Machine learning techniques reached a higher level of success. Especially, Deep Learning (DL). The purpose of this work, is to investigate the application of DL techniques in the problem of Face Recognition. In fact, Face Recognition is a currently developing technology with multiple real-life applications. In particular, Facial Hair Recognition/detection plays an important role in improving Face Recognition The goal of this work is to develop a Facial Hair system. Recognition (FHR) system using DL. The developed system uses Convolutional Neural Networks (CNNS), which is capable of learning and improving its performance without the need of human intervention. The system can be trained to distinguish between faces that have a beard and/or moustache and the shaved faces by learning from faces dataset. We compared our system's results with a non deep learning based system, where our system achieved promising results with accuracy surpassed 77% for a set of 800 images.
note de thèses :	Mémoire de master en informatique

Face recognition using Deep Learning [texte manuscrit] / Ibrahim Chorana, Auteur ; Younes Guellouma, Directeur de thèse . - Laghouat : Université Amar Telidji - Département d'informatique, 2018 . - 60 p. ; 30 cm. + 1 disque optique numérique (CD-ROM).
Option : (Decision-making information systems) Systèmes d'information et de décision
Langues : Anglais

Mots-clés :	Machine Learning  Deep Learning  CNNS  Face Recognition  Facial hair Recognition
Résumé :	Nowdays, Machine learning techniques reached a higher level of success. Especially, Deep Learning (DL). The purpose of this work, is to investigate the application of DL techniques in the problem of Face Recognition. In fact, Face Recognition is a currently developing technology with multiple real-life applications. In particular, Facial Hair Recognition/detection plays an important role in improving Face Recognition The goal of this work is to develop a Facial Hair system. Recognition (FHR) system using DL. The developed system uses Convolutional Neural Networks (CNNS), which is capable of learning and improving its performance without the need of human intervention. The system can be trained to distinguish between faces that have a beard and/or moustache and the shaved faces by learning from faces dataset. We compared our system's results with a non deep learning based system, where our system achieved promising results with accuracy surpassed 77% for a set of 800 images.
note de thèses :	Mémoire de master en informatique