Comparison of multidimensional data access methods for feature-based image retrieval


Arslan S., Saçan A., Açar E., TOROSLU İ. H. , YAZICI A.

2010 20th International Conference on Pattern Recognition, ICPR 2010, İstanbul, Turkey, 23 - 26 August 2010, pp.3260-3263 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/icpr.2010.797
  • City: İstanbul
  • Country: Turkey
  • Page Numbers: pp.3260-3263

Abstract

Within the scope of information retrieval, efficient similarity search in large document or multimedia collections is a critical task. In this paper, we present a rigorous comparison of three different approaches to the image retrieval problem, including cluster-based indexing, distance-based indexing, and multidimensional scaling methods. The time and accuracy tradeoffs for each of these methods are demonstrated on a large Corel image database. Similarity of images is obtained via a featurebased similarity measure using four MPEG-7 low-level descriptors. We show that an optimization of feature contributions to the distance measure can identify irrelevant features and is necessary to obtain the maximum accuracy. We further show that using multidimensional scaling can achieve comparable accuracy, while speeding-up the query times significantly by allowing the use of spatial access methods. © 2010 IEEE.