Semi-automatic region of interest identification algorithm using wavelets

Sedig Salem Agili; Vittal Balasubramanian; Aldo W. Morales

doi:10.1117/1.2713377

1 March 2007 Semi-automatic region of interest identification algorithm using wavelets

Sedig Salem Agili, Vittal Balasubramanian, Aldo W. Morales

Author Affiliations +

Optical Engineering, Vol. 46, Issue 3, 035003 (March 2007). https://doi.org/10.1117/1.2713377

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.

©(2007) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Sedig Salem Agili, Vittal Balasubramanian, and Aldo W. Morales "Semi-automatic region of interest identification algorithm using wavelets," Optical Engineering 46(3), 035003 (1 March 2007). https://doi.org/10.1117/1.2713377

Published: 1 March 2007

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available