Share Email Print

Optical Engineering

Semi-automatic region of interest identification algorithm using wavelets
Author(s): Sedig Salem Agili; Vittal Balasubramanian; Aldo W. Morales
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Typically, the region of interest (ROI), in the JPEG2000 standard, is manually defined, and then wavelets are used to compress the ROI at a higher bitrate than the rest of the image. The wavelet decomposition in JPEG2000 also lends itself to texture and edge extraction for segmentation and classification purposes. In this paper, a semi-automatic ROI generation algorithm for images is presented, where the texture and edge information provided by the first level of the wavelet decomposition is used to segment the wavelet coefficients. This first-level decomposition provides enough edge and texture information for image segmentation, allowing computational savings. A mask that outlines the ROI is determined based on the entropy calculation of the segmented regions. The advantage of this method is that the segmentation process is entirely performed in the wavelet and not in the pixel domain, therefore offering additional computational efficiency. The resulting ROI is coded using the MAXSHIFT method. The algorithm was applied and successfully demonstrated in several images.

Paper Details

Date Published: 1 March 2007
PDF: 6 pages
Opt. Eng. 46(3) 035003 doi: 10.1117/1.2713377
Published in: Optical Engineering Volume 46, Issue 3
Show Author Affiliations
Sedig Salem Agili, The Pennsylvania State Univ. (United States)
Vittal Balasubramanian, The Pennsylvania State Univ. (United States)
Aldo W. Morales, The Pennsylvania State Univ. (United States)

© SPIE. Terms of Use
Back to Top