RT Journal Article
A1 David Hanwell
AD Visual Information Laboratory, Department of Computer Science, University of Bristol, Bristol, UK
A1 Majid Mirmehdi
AD Visual Information Laboratory, Department of Computer Science, University of Bristol, Bristol, UK

PB iet
T1 Weakly supervised learning of semantic colour terms
JN IET Computer Vision
VO 8
IS 2
SP 110
OP 117
AB 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, which are expensive and time consuming to produce. The authors propose a method which uses raw, noisy and unsegmented results of web image searches, to learn semantic colour terms. They use probabilistic graphical models on continuous domain, both for weakly supervised learning, and for segmentation of novel images. Experiments show that the authors methods give better results than the current state of the art in colour naming using noisy, weakly labelled training data. *Note: Colour figures are available in the online version of this paper.
K1 probabilistic graphical models
K1 semantic colour terms
K1 visual attribute recognition
K1 image archiving
K1 image recognition
K1 noisy weakly labelled training data
K1 image information content
K1 weakly supervised learning
K1 manually segmented image classification
K1 Web image searches
K1 image segmentation
DO https://doi.org/10.1049/iet-cvi.2012.0210
UL https://digital-library.theiet.org/;jsessionid=2aeidhr5bl8gq.x-iet-live-01content/journals/10.1049/iet-cvi.2012.0210
LA English
SN 1751-9632
YR 2014
OL EN