A successively refinable wavelet-based representation for content-based image retrieval

S. Servetto, K. Ramchandran, T. S. Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Content based retrieval of image and video data from databases is a very challenging problem, whose interest is dedved from the need of future databases to support efficient access to vast amounts of visual information. Typical queries to be performed in this context check attributes of objects present in image data, such as shape, color, relative locations, etc. Therefore, the way in which image data is represented plays a fundamental role in the efficient implementation of those queries. One possibility is to take the naive approach of storing images using standard compression techniques, storing image features (such as object shape descriptors, color histograms, etc.) as explicit side information, and whenever an image is involved in the evaluation of a query decoding it to full resolution; however, much more efficient techniques (in terms of storage and computational requirements) are possible. In this paper, we propose a new image coding technique which combines a wavelet image representation, embedded coding of the wavelet coefficients, and segmentation of semantically meaningful objects in the wavelet domain, to generate a bitstream in which each object is encoded independently of every other object in the image, and without explicitly storing shape boundary information. Furthermore, since the representation of each object is fully embedded applications may, independently for each object, specify the desired target bitrate and retrieve bits from the compressed bitstream. Preliminary results show that our new proposed method achieves PSNR numbers within 0.3dB of those achieved using the same coder without including segmentation information (which is one of the best within its class), thus showing that no severe performance loss results from enabling independent access to objects in the compressed domain.

Original languageEnglish (US)
Title of host publication1997 IEEE 1st Workshop on Multimedia Signal Processing, MMSP 1997
EditorsYao Wang, Amy R. Reibman, B. H. Juang, Tsuhan Chen, Sun-Yuan Kung
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages325-330
Number of pages6
ISBN (Electronic)0780337808, 9780780337800
DOIs
StatePublished - Jan 1 1997
Event1st IEEE Workshop on Multimedia Signal Processing, MMSP 1997 - Princeton, United States
Duration: Jun 23 1997Jun 25 1997

Publication series

Name1997 IEEE 1st Workshop on Multimedia Signal Processing, MMSP 1997

Other

Other1st IEEE Workshop on Multimedia Signal Processing, MMSP 1997
CountryUnited States
CityPrinceton
Period6/23/976/25/97

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology

Fingerprint Dive into the research topics of 'A successively refinable wavelet-based representation for content-based image retrieval'. Together they form a unique fingerprint.

  • Cite this

    Servetto, S., Ramchandran, K., & Huang, T. S. (1997). A successively refinable wavelet-based representation for content-based image retrieval. In Y. Wang, A. R. Reibman, B. H. Juang, T. Chen, & S-Y. Kung (Eds.), 1997 IEEE 1st Workshop on Multimedia Signal Processing, MMSP 1997 (pp. 325-330). [602656] (1997 IEEE 1st Workshop on Multimedia Signal Processing, MMSP 1997). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MMSP.1997.602656