Semi-automatic region of interest identification algorithm using wavelets

Sedig Salem Agili, Vittal Balasubramanian, Aldo W. Morales

Research output: Contribution to journalArticle

2 Citations (Scopus)

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 out-lines 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.

Original languageEnglish (US)
Article number035003
JournalOptical Engineering
Volume46
Issue number3
DOIs
StatePublished - Mar 1 2007

Fingerprint

Wavelet decomposition
Textures
textures
decomposition
Computational efficiency
Image segmentation
Masks
Entropy
Pixels
masks
pixels
entropy
coefficients

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Engineering(all)

Cite this

@article{07f71e9be0f249bdb8ec83972e3ff1a1,
title = "Semi-automatic region of interest identification algorithm using wavelets",
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 out-lines 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.",
author = "Agili, {Sedig Salem} and Vittal Balasubramanian and Morales, {Aldo W.}",
year = "2007",
month = "3",
day = "1",
doi = "10.1117/1.2713377",
language = "English (US)",
volume = "46",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "3",

}

Semi-automatic region of interest identification algorithm using wavelets. / Agili, Sedig Salem; Balasubramanian, Vittal; Morales, Aldo W.

In: Optical Engineering, Vol. 46, No. 3, 035003, 01.03.2007.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Semi-automatic region of interest identification algorithm using wavelets

AU - Agili, Sedig Salem

AU - Balasubramanian, Vittal

AU - Morales, Aldo W.

PY - 2007/3/1

Y1 - 2007/3/1

N2 - 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 out-lines 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.

AB - 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 out-lines 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.

UR - http://www.scopus.com/inward/record.url?scp=34447257160&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34447257160&partnerID=8YFLogxK

U2 - 10.1117/1.2713377

DO - 10.1117/1.2713377

M3 - Article

VL - 46

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 3

M1 - 035003

ER -