Paper Info
Title
A systematic study of the role of context on image classification
Abstract
ABSTRACT We present the results of a systematic study of the contextual gain hypothesis for image classification. This hypothesis relates the tradi- tional strategy of direct visual classification (DVC), and an alterna- tive strategy based on indirect contextual classification (ICC). DVC is composed,of classifiers that operate directly on pixel or feature based image,representations. ICC relies on DVC to label images with respect to a pre-defined set of contextual semantic features. Im- age classification is then performed,by a classifier that operates on the semantic space of these classifier outputs. The contextual gain hypothesis states that, in this semantic space, it is possible to de- sign classifiers with better accuracy than those achievable with DVC. A framework,for the systematic comparison,of the DVC and ICC strategies is introduced, and an extensive comparison of the perfor- mance,of the two strategies is carried out. Its results strongly suggest that the contextual gain hypothesis holds. Index Terms— Image analysis, image classification, contextual
Year
DOI
Venue
2008
10.1109/ICIP.2008.4712106
San Diego, CA
Keywords
Field
DocType
feature extraction,image classification,image representation,visual perception,contextual semantic feature,direct visual classification,image classification,image representation,indirect contextual gain hypothesis,Image analysis,contextual learning,image classification,image retrieval,semantic space
Computer science,Contextual learning,Image retrieval,Artificial intelligence,Classifier (linguistics),Contextual image classification,Visual perception,Computer vision,Pattern recognition,Visualization,Feature extraction,Pixel,Machine learning
Conference
ISSN
ISBN
Citations 
1522-4880 E-ISBN : 978-1-4244-1764-3
978-1-4244-1764-3
0
PageRank 
References 
Authors
0.34
7
2
Name
Order
Citations
PageRank
N Rasiwasia1117334.61
Nuno Vasconcelos25410273.99