Veuillez utiliser cette adresse pour citer ce document :
http://dspace.univ-tiaret.dz:80/handle/123456789/5324
Titre: | Le deep learning pour la classification des images dans différents système de couleur. |
Auteur(s): | Hatem, M’hamed Amine |
Mots-clés: | Deep learning, Color-spaces, Convolutional Neural Networks, ResNet, CapsuleNet |
Date de publication: | 2019 |
Editeur: | Université Ibn Khaldoun -Tiaret- |
Résumé: | Image classification is fundamental in the field of artificial intelligence, recently Deep Residual Learning [1] and the new coming model CapsulNet[2] have shown state-of-the-art performance for image classification tasks , they takes data-sets mostly as input in the form of RGB images even though we have many other colorspaces available. In this thesis we try to understand the impact of image color-space on the performance of CNN models in Image classification . We evaluate this on CIFAR10 [3]data-set by converting it into five other color-spaces HLS, HSV, LUV, LAB, YUV and trained each one of them in two different deep learning architecture models namely ResNet20 and CapsulNet , the results obtained show a minor change in accuracy but even a small percentage may make the difference, in the other hand LUV is good alternative it show improvement about 0.92% comparison to RGB in ResNet20 and 0.39% in CapsulNet. |
URI/URL: | http://dspace.univ-tiaret.dz:80/handle/123456789/5324 |
Collection(s) : | Master |
Fichier(s) constituant ce document :
Fichier | Description | Taille | Format | |
---|---|---|---|---|
TH.M.INF.FR.2019.26.pdf | 3,13 MB | Adobe PDF | Voir/Ouvrir |
Tous les documents dans DSpace sont protégés par copyright, avec tous droits réservés.