Deep filter banks for texture recognition and segmentation

Research in texture recognition often concentrates on the problem of material recognition in uncluttered conditions, an assumption rarely met by applications. In this work we conduct a first study of material and describable texture attributes recognition in clutter, using a new dataset derived from...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) S. 3828 - 3836
Hauptverfasser:	Cimpoi, Mircea, Maji, Subhransu, Vedaldi, Andrea
Format:	Tagungsbericht Journal Article
Sprache:	Englisch
Veröffentlicht:	IEEE 01.06.2015
Schlagworte:	Accuracy Benchmark testing Clutter Construction Feature extraction Image recognition Image segmentation Segmentation Shape State of the art Surface layer Texture Texture recognition
ISSN:	1063-6919, 1063-6919
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!