| Titre : | Visual content compression using Deep Learning techniques |
| Auteurs : | RAHMANI Lamia, Auteur ; HAMOU Fatima, Auteur ; MOKADEM Djelloul, Directeur de thèse |
| Type de document : | texte imprimé |
| Editeur : | Université Saïda– Dr. Tahar Moulay – Faculté de Technologie DBR.Télécommunications, 2023/2024 |
| Format : | 65 p |
| Accompagnement : | CD |
| Langues: | Anglais |
| Langues originales: | Anglais |
| Mots-clés: | visual content ; compression ; CNN ; deep learning. deep |
| Résumé : |
In recent years, the quantity of visual content continues to increase
day after day, which is mainly linked to the rise of social networks and video streaming platforms. Even as storage and transmission capacities improve, this growing number of transmitted images and videos requires more efficient compression methods. Lossy image compression achieves high compression ratios by eliminating information that does not contribute to human perception of images, or that contributes as little as possible. Due to the limitations of the human visual system, such information loss may be acceptable in many scenarios, but the visual artifacts introduced become unacceptable at higher compression ratios. The project focuses on the JPEG compression method and the degradations it causes. It is a challenging task since there are highly complex unknown correlations between the pixels, as a result, it is hard to find and recover them. We want to find a well-compressed representation for images and, design and test networks that are able to recover it successfully in a lossless or lossy way. we will try to useconvolutional neural networks (CNN) learning based to achieve the goal we have fixed |
Exemplaires
| Code-barres | Cote | Support | Localisation | Section | Disponibilité |
|---|---|---|---|---|---|
| aucun exemplaire |
Documents numériques (1)
Visual content compression using Deep Learning techniques Adobe Acrobat PDF |
