Weakly supervised learning of semantic colour terms

Weakly supervised learning of semantic colour terms

Recognition of visual attributes in images allows an image's information content to be expressed textually. This has benefits for web search and image archiving, especially since visual attributes transcend language barriers. Classifiers are traditionally trained using manually segmented images...

Full description

Bibliographic Details
Main Authors: David Hanwell, Majid Mirmehdi
Format: Article
Language:English
Published: Wiley 2014-04-01
Series:IET Computer Vision
Subjects:
semantic colour terms
weakly supervised learning
visual attribute recognition
image recognition
image information content
image archiving
Online Access:https://doi.org/10.1049/iet-cvi.2012.0210

Internet

https://doi.org/10.1049/iet-cvi.2012.0210

Similar Items