dc.contributor.author |
Ayoub, AOULALAY |
|
dc.contributor.author |
El MHOUTI, Abderrahim |
|
dc.contributor.author |
MASSAR, Mohammed |
|
dc.date.accessioned |
2024-01-09T13:32:24Z |
|
dc.date.available |
2024-01-09T13:32:24Z |
|
dc.date.issued |
2024-01-09 |
|
dc.identifier.uri |
https://journal.uob.edu.bh:443/handle/123456789/5330 |
|
dc.description.abstract |
Texture analysis, a vital component of computer vision and image processing, plays a pivotal role in fields such as
decoration and art. This study focuses on the classification of regular textures into 17 distinct wallpaper patterns based on
their symmetry operations. Utilizing computer vision techniques and a filter bank approach, we compared three methods:
Gabor filter bank, CNN-trained filters, and ImageNet pretrained filters, in conjunction with a random forest model. The results
revealed that ImageNet pretrained filters performed exceptionally well, achieving 87% accuracy in the 'wallpaper17' dataset
and 81% in the 'wallpaper04' dataset. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
University of Bahrain |
en_US |
dc.subject |
texture classification; wallpaper geometric groupes; filter bank; deep convolutional neural network |
en_US |
dc.title |
Symmetry-Based Classification of Regular Textures based on filters bank and Random Forest |
en_US |
dc.identifier.doi |
10.12785/ijcds/xxxxxx |
|
dc.volume |
15 |
en_US |
dc.issue |
1 |
en_US |
dc.pagestart |
1 |
en_US |
dc.pageend |
9 |
en_US |
dc.contributor.authorcountry |
Tetouan, Morocco |
en_US |
dc.contributor.authorcountry |
Tetouan, Morocco |
en_US |
dc.contributor.authorcountry |
Morocco |
en_US |
dc.contributor.authoraffiliation |
ISISA, FS, Abdelmalek Essaadi University |
en_US |
dc.contributor.authoraffiliation |
ISISA, FS, Abdelmalek Essaadi University |
en_US |
dc.contributor.authoraffiliation |
Analyse Non Linéaire Appliquée |
en_US |
dc.source.title |
International Journal of Computing and Digital Systems |
en_US |
dc.abbreviatedsourcetitle |
IJCDS |
en_US |