Adaptive color-image embeddings for database navigation


Conference Paper

© Springer-Verlag Berlin Heidelberg 1997. We present a novel approach to the problem of navigating through a database of color images for the purpose of image retrieval. We endow the database with a metric for the color distributions of the images. We then use multi-dimensional scaling techniques to embed a group of images as points in a two-dimensional Euclidean space so that their distances reflect image dissimilarities as well as possible. Such geometric embeddings allow the user to perceive the dominant axes of variation in the displayed image group, and form a mental picture of the database contents. Furthermore, since these embeddings group similar images together, away from dissimilar ones, the user can refine the query in a perceptually intuitive way. By iterating this process, the user can quickly navigate to the portion of the image space of interest.

Full Text

Duke Authors

Cited Authors

  • Rubner, Y; Tomasi, C; Guibas, LJ

Published Date

  • January 1, 1997

Published In

Volume / Issue

  • 1351 /

Start / End Page

  • 104 - 111

Electronic International Standard Serial Number (EISSN)

  • 1611-3349

International Standard Serial Number (ISSN)

  • 0302-9743

International Standard Book Number 10 (ISBN-10)

  • 3540639306

International Standard Book Number 13 (ISBN-13)

  • 9783540639305

Digital Object Identifier (DOI)

  • 10.1007/3-540-63930-6_110

Citation Source

  • Scopus