G. Qiu et al. (Eds.): PCM 2010, Part I, LNCS 6297, pp. 515–526, 2010.
© Springer-Verlag Berlin Heidelberg 2010
Unifying Content and Context Similarities of the Textual
and Visual Information in an Image Clustering
Framework
Bashar Tahayna
1
, Saadat M. Alashmi
1
, Mohammed Belkhatir
2
, Khaled Abbas
3
,
and Yandan Wang
1
1
Monash University, Sunway Campus
2
Université Claude Bernard Lyon 1, France
3
University of Malaya, Malaysia
{bashar.tahayna,saadat.m.alhashmi,
yandan.wang}@infotech.monash.edu.my,
mohammed.belkhatir@iut.univ-lyon1.fr,
khaled@perdana.um.edu.my
Abstract. Content-based image retrieval (CBIR) has been a challenging prob-
lem and its performance relies on the efficiency in modeling the underlying
content and the similarity measure between the query and the retrieved images.
Most existing metrics evaluate pairwise image similarity based only on image
content, which is denoted as content similarity. However, other schemes utilize
the annotations and the surrounding text to improve the retrieval results. In this
study we refer to content as the visual and the textual information belonging to
an image. We propose a representation of an image surrounding text in terms of
concepts by utilizing an online knowledge source, e.g., Wikipedia, and propose
a similarity metric that takes into account the new conceptual representation of
the text. Moreover, we combine the content information with the contexts of an
image to improve the retrieval percentage. The context of an image is built by
constructing a vector with each dimension representing the content (visual and
textual/conceptual) similarity between the image and any image in the collec-
tion. The context similarity between two images is obtained by computing the
similarity between the corresponding context vectors using the vector similarity
functions. Then, we fuse the similarity measures into a unified measure to
evaluate the overall image similarity. Experimental results demonstrate that the
new text representation and the use of the context similarity can significantly
improve the retrieval performance.
Keywords: Clustering, Classification, Content-based, Similarity measures,
bipitrate graphs.
1 Introduction and Related Work
Human’s perceptual abilities, analysis and reasoning tend to describe images with
words, even with biased description, effectively and efficiently. Unfortunately, this is
not the case with the current computer systems and algorithms. For example, in Yahoo