Paper Info
Title
Active learning paradigms for CBIR systems based on optimum-path forest classification
Abstract
This paper discusses methods for content-based image retrieval (CBIR) systems based on relevance feedback according to two active learning paradigms, named greedy and planned. In greedy methods, the system aims to return the most relevant images for a query at each iteration. In planned methods, the most informative images are returned during a few iterations and the most relevant ones are only presented afterward. In the past, we proposed a greedy approach based on optimum-path forest classification (OPF) and demonstrated its gain in effectiveness with respect to a planned method based on support-vector machines and another greedy approach based on multi-point query. In this work, we introduce a planned approach based on the OPF classifier and demonstrate its gain in effectiveness over all methods above using more image databases. In our tests, the most informative images are better obtained from images that are classified as relevant, which differs from the original definition. The results also indicate that both OPF-based methods require less user involvement (efficiency) to satisfy the user's expectation (effectiveness), and provide interactive response times.
Year
DOI
Venue
2011
10.1016/j.patcog.2011.04.026
Pattern Recognition
Keywords
DocType
Volume
active learning,informative image,greedy method,planned method,image databases,relevance feedback,planned approach,optimum-path forest classifiers,optimum-path forest classification,image pattern analysis,relevant image,cbir system,opf classifier,active learning paradigm,multi-point query,greedy approach,content-based image retrieval,pattern analysis,support vector machine,satisfiability
Journal
44
Issue
ISSN
Citations 
12
Pattern Recognition
24
PageRank 
References 
Authors
0.84
29
3
Name
Order
Citations
PageRank
André Tavares da Silva1462.93
Alexandre Xavier Falcão216710.22
Léo Pini Magalhães3677.69