Regular Article
A Flexible Image Database System for Content-Based Retrieval

https://doi.org/10.1006/cviu.1999.0772Get rights and content

Abstract

There is a growing need for the ability to query image databases based on similarity of image content rather than strict keyword search. As distance computations can be expensive, there is a need for indexing systems and algorithms that can eliminate candidate images without performing distance calculations. As user needs may change from session to session, there is also a need for run-time creation of distance measures. In this paper, we present FIDS, “flexible image database system.” FIDS allows the user to query the database based on complex combinations of dozens of predefined distance measures. Using an indexing scheme and algorithms based on the triangle inequality, FIDS can often return matches to the query image without directly comparing the query image to more than a small percentage of the database. This paper describes the technical contributions of the FIDS approach to content-based image retrieval.

References (45)

  • W.I. Grosky et al.

    Index-based object recognition in pictorial data management

    Comput. Vision Graphics and Image Processing.

    (1990)
  • A.K. Jain et al.

    Image retrieval using color and shape

    Pattern Recognition

    (1996)
  • J. Uhlmann

    Satisfying general proximity/similarity queries with metric trees

    Information Processing Letters

    (1991)
  • L. Wang et al.

    Texture classification using texture spectrum

    Pattern Recognit. Lett.

    (1990)
  • J.R. Bach et al.

    A visual information management system for the interactive retrieval of faces

    IEEE Trans. Knowledge Data Eng.

    (1993)
  • R. Baeza-Yates et al.

    Proximity matching using fixed-queries trees

    Combinatorial Pattern Matching

    (1994)
  • J. Barros, J. French, W. Martin, P. Kelley, and, M. Cannon, Using the triangle inequality to reduce the number of...
  • A. Berman

    A New Data Structure for Fast Approximate Matching

    (1994)
  • A. Berman, and, L. G. Shapiro, A flexible image database system for content-based retrieval, in, 17th International...
  • A. P. Berman, and, L. G. Shapiro, Efficient image retrieval with multiple distance measures, in, Proceedings of the...
  • A. Del Bimbo et al.

    3d visual query language for image databases

    J. Visual Lang. Comput.

    (1992)
  • A. Del Bimbo, P. Pala, and S. Santini, Visual image retrieval by elastic deformation of object sketches, in IEEE...
  • A. Del Bimbo, E. Vicario, and D. Zingoni, Sequence retrieval by contents through spatio temporal indexing. In IEEE...
  • W. A. Burkhard, and, R. M. Keller, Some approaches to best-match file searching, Comm....
  • C. Carson, S. Belongie, H. Greenspan, and J. Malik, Region-based image querying, in IEEE Workshop on Content-Based...
  • S.K. Chang et al.

    Design considerations of a pictorial database system

    Int. J. Policy Anal. Inf. Systems

    (1978)
  • S.K. Chang et al.

    Iconic indexing by 2d strings

    IEEE Trans. Pattern Anal. Mach. Intell.

    (1987)
  • R. Fagin, Fuzzy queries in multimedia database systems, in Proceedings of the 17th ACM SIGACT-SIGMOD-SIGART Symposium...
  • M.M. Fleck et al.

    Finding naked people

    Proceedings of the European Conference on Computer Vision

    (1996)
  • M. Flickner et al.

    Query by image and video content: The QBIC system

    Computer

    (1995)
  • D. A. Forsyth, J. Malik, M. M. Fleck, H. Greenspan, T. Leung, S. Belongie, C. Carson, and, C. Bregler, Finding pictures...
  • A. Gupta

    Visual Information Retrieval: A Virage Perspective

    (1995)
  • Cited by (68)

    • Recent developments of content-based image retrieval (CBIR)

      2021, Neurocomputing
      Citation Excerpt :

      In fact, this algorithm can combine any number of different feature types without any modeling assumptions. Berman et al. [14] presented a set of operations for combining features and proposed a Flexible Image Database System (FIDS) in which the gridded distance measures and combining operations can also combine any group of multiple types of features. Moreover, Zhao et al. [15] adopted the Sparse Representation (SR) into image retrieval.

    • An efficient technique for retrieval of color images in large databases

      2015, Computers and Electrical Engineering
      Citation Excerpt :

      The similarity score between a query and a database image is calculated as a weighted sum of the distances between the two color vectors and shape descriptors. In FIDS (Flexible Image Database System) [6], the distance between wavelet coefficients, is some weighted difference. An overall distance can be calculated by taking the weighted sum, maximum, or minimum of the individual feature distances, which preserves metric properties.

    • Monitoring of illicit pill distribution networks using an image collection exploration framework

      2012, Forensic Science International
      Citation Excerpt :

      Local binary patterns. Local binary patterns [24] are a measure of image texture. The goal is to define a set of binary patterns (black and white) that can be found around each pixel.

    • Content-based histopathology image retrieval using a kernel-based semantic annotation framework

      2011, Journal of Biomedical Informatics
      Citation Excerpt :

      For instance, as it is shown in Fig. 1, the NPC pattern, highlighted in dotted lines (green), contains a mixture of the textures inside the nodule, the edges provided by the cleft, and the density of the palisading cells. To describe the different visual characteristics of histopathology patterns, seven feature spaces have been selected: gray scale histogram, invariant feature histogram [24], local binary patterns [25], RGB color histogram [24], bag of SIFT features, Sobel histogram [26] and Tamura texture histogram [27]. These seven low-level features are complementary with respect to the kind of measure they do over image pixels, since they apply different computations to build the histograms.

    View all citing articles on Scopus

    This research was partially supported by the National Science Foundation under Grant IRI-9711771.

    Corresponding author.

    f1

    [email protected], [email protected]

    View full text