Deep convolutional features for image retrieval

•A comprehensive study that explores deep convolutional features for CBIR.•The paper evaluates recently proposed CNNs architectures in image retrieval tasks.•A plug-n-play approach that uses new architectures of pre-trained CNN’s for CBIR.•The performance of each network is evaluated using global an...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Expert systems with applications 2021-09, Vol.177, p.114940, Article 114940
Hauptverfasser:	Gkelios, Socratis, Sophokleous, Aphrodite, Plakias, Spiros, Boutalis, Yiannis, Chatzichristofis, Savvas A.
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks CBIR CNN Complexity Computer vision Deep convolutional features Deep learning Global features Image classification Image management Image retrieval Local features Optimization State-of-the-art reviews
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!