Abstract
When constructing basis functions of a transform, the prime consideration is the localization, i.e., the characterization of local properties, of the basis functions in time and frequency. The signals we are concerned with are 2-D color or gray-scale images, for which the time domain is the spatial location of a pixel, and the frequency domain is the color variation around a pixel. We thus seek a transform that can effectively represent color variations in any local spatial region of the image so that selected coefficients of this transform can be used in the image feature vector. In this chapter, we compare various transforms and their properties to select a transform suitable for CBIR.
Mathematics is the art of giving the same name to different things. — Jules Henri Poincare (1854–1912)
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer Science+Business Media New York
About this chapter
Cite this chapter
Wang, J.Z. (2001). Wavelets. In: Integrated Region-Based Image Retrieval. The Information Retrieval Series, vol 11. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-1641-5_3
Download citation
DOI: https://doi.org/10.1007/978-1-4615-1641-5_3
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-5655-4
Online ISBN: 978-1-4615-1641-5
eBook Packages: Springer Book Archive