Share Email Print

Proceedings Paper

A novel method for efficient archiving and retrieval of biomedical images using MPEG-7
Author(s): Joerg Meyer; Ash Pahwa
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Digital archiving and efficient retrieval of radiological scans have become critical steps in contemporary medical diagnostics. Since more and more images and image sequences (single scans or video) from various modalities (CT/MRI/PET/digital X-ray) are now available in digital formats (e.g., DICOM-3), hospitals and radiology clinics need to implement efficient protocols capable of managing the enormous amounts of data generated daily in a typical clinical routine. We present a method that appears to be a viable way to eliminate the tedious step of manually annotating image and video material for database indexing. MPEG-7 is a new framework that standardizes the way images are characterized in terms of color, shape, and other abstract, content-related criteria. A set of standardized descriptors that are automatically generated from an image is used to compare an image to other images in a database, and to compute the distance between two images for a given application domain. Text-based database queries can be replaced with image-based queries using MPEG-7. Consequently, image queries can be conducted without any prior knowledge of the keys that were used as indices in the database. Since the decoding and matching steps are not part of the MPEG-7 standard, this method also enables searches that were not planned by the time the keys were generated.

Paper Details

Date Published: 25 October 2004
PDF: 9 pages
Proc. SPIE 5600, Multimedia Systems and Applications VII, (25 October 2004); doi: 10.1117/12.571469
Show Author Affiliations
Joerg Meyer, Univ. of California/Irvine (United States)
Ash Pahwa, DV Studio Inc. (United States)

Published in SPIE Proceedings Vol. 5600:
Multimedia Systems and Applications VII
Chang Wen Chen; C.-C. Jay Kuo; Anthony Vetro, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?