| Titre : | Approaches and Techniques for Facial Recognition |
| Auteurs : | Wafaa Fellah, Auteur ; Mohamed Elhabib Louafi, Auteur ; Meriem Meddber, Directeur de thèse |
| Type de document : | texte manuscrit |
| Editeur : | Université mustapha stambouli de Mascara:Faculté des sciences exactes, 2023 |
| ISBN/ISSN/EAN : | SE02369T |
| Format : | 76P. / couv. ill. / 29cm. |
| Accompagnement : | disque optique numérique (CD-ROM) |
| Langues: | Anglais |
| Résumé : |
Facial recognition is a rapidly growing research field, offering numerous practical applications such as security, surveillance, and identity verification or identification. In this memory, we focused on the use of deep learning, specifically convolutional neural networks (CNN), and transfer learning using the VGG model. firstly, we conducted a literature review to understand the key concepts and approaches used in deep learning-based facial recognition. We examined the architectures of convolutional neural networks in detail, with a focus on their ability to extract meaningful features from facial images. We also studied the concept of transfer learning, which involves reusing pre-trained models on large datasets. Next, we implemented a facial recognition system using CNN as the base architecture. Subsequently, we introduced transfer learning using the VGG model. Validating the results of our work over a created local dataset using data augmentation technique with a deployment of both approaches using a desktop application. Keywords: Facial Recognition, Computer Vision, Deep Learning, Transfer Learning, Neural Network, Convolutional Neural Network |
Exemplaires (1)
| Code-barres | Cote | Support | Localisation | Section | Disponibilité |
|---|---|---|---|---|---|
| SE02369T | INF955 | Livre audio | Bibliothèque des Sciences Exactes | 7-Mémoires Master | Consultation sur place Exclu du prêt |
Aucun avis, veuillez vous identifier pour ajouter le vôtre !
Accueil
