Fast watershed aided by target detection

Huibao Lin; Jennie Si; Glen P. Abousleman

doi:10.1117/12.470102

Fast watershed aided by target detection

Huibao Lin, Jennie Si, Glen P. Abousleman

Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

The Watershed algorithm has been studied extensively, and has been applied to image segmentation due to its accuracy and robustness. However, the watershed requires a large amount of memory; and is computationally interactable for segmenting large images. In this paper, we introduce a novel hierarchical region-of-interest (ROI) detection scheme, which is used as a prelude to segmentation. With the help of the detection algorithm, watershed segmentation can be applied to the small detected regions, rather than to the entire image. Therefore, it can process large images by selectively segmenting ROIs. We focus on our new ROI detection algorithm, and how it is integrated into a system for large-image segmentation. We demonstrate the efficiency of the proposed scheme by processing a variety of images.

Original language	English (US)
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Editors	D.P. Casasent, A.G. Tescher
Pages	1-12
Number of pages	12
Volume	4735
DOIs	https://doi.org/10.1117/12.470102
State	Published - 2002
Event	Hybrid Image and Signal Processing VIII - Orlando, FL, United States Duration: Apr 4 2002 → Apr 4 2002

Other

Other	Hybrid Image and Signal Processing VIII
Country/Territory	United States
City	Orlando, FL
Period	4/4/02 → 4/4/02

Keywords

Hybrid image segmentation
Regions-of-interest
Target detection
Watershed

ASJC Scopus subject areas

Electrical and Electronic Engineering
Condensed Matter Physics

Access to Document

10.1117/12.470102

Cite this

@inproceedings{5262c7a95f6e4ec68d83cf3d40228a44,

title = "Fast watershed aided by target detection",

abstract = "The Watershed algorithm has been studied extensively, and has been applied to image segmentation due to its accuracy and robustness. However, the watershed requires a large amount of memory; and is computationally interactable for segmenting large images. In this paper, we introduce a novel hierarchical region-of-interest (ROI) detection scheme, which is used as a prelude to segmentation. With the help of the detection algorithm, watershed segmentation can be applied to the small detected regions, rather than to the entire image. Therefore, it can process large images by selectively segmenting ROIs. We focus on our new ROI detection algorithm, and how it is integrated into a system for large-image segmentation. We demonstrate the efficiency of the proposed scheme by processing a variety of images.",

keywords = "Hybrid image segmentation, Regions-of-interest, Target detection, Watershed",

author = "Huibao Lin and Jennie Si and Abousleman, {Glen P.}",

year = "2002",

doi = "10.1117/12.470102",

language = "English (US)",

volume = "4735",

pages = "1--12",

editor = "D.P. Casasent and A.G. Tescher",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

note = "Hybrid Image and Signal Processing VIII ; Conference date: 04-04-2002 Through 04-04-2002",

}

TY - GEN

T1 - Fast watershed aided by target detection

AU - Lin, Huibao

AU - Si, Jennie

AU - Abousleman, Glen P.

PY - 2002

Y1 - 2002

N2 - The Watershed algorithm has been studied extensively, and has been applied to image segmentation due to its accuracy and robustness. However, the watershed requires a large amount of memory; and is computationally interactable for segmenting large images. In this paper, we introduce a novel hierarchical region-of-interest (ROI) detection scheme, which is used as a prelude to segmentation. With the help of the detection algorithm, watershed segmentation can be applied to the small detected regions, rather than to the entire image. Therefore, it can process large images by selectively segmenting ROIs. We focus on our new ROI detection algorithm, and how it is integrated into a system for large-image segmentation. We demonstrate the efficiency of the proposed scheme by processing a variety of images.

AB - The Watershed algorithm has been studied extensively, and has been applied to image segmentation due to its accuracy and robustness. However, the watershed requires a large amount of memory; and is computationally interactable for segmenting large images. In this paper, we introduce a novel hierarchical region-of-interest (ROI) detection scheme, which is used as a prelude to segmentation. With the help of the detection algorithm, watershed segmentation can be applied to the small detected regions, rather than to the entire image. Therefore, it can process large images by selectively segmenting ROIs. We focus on our new ROI detection algorithm, and how it is integrated into a system for large-image segmentation. We demonstrate the efficiency of the proposed scheme by processing a variety of images.

KW - Hybrid image segmentation

KW - Regions-of-interest

KW - Target detection

KW - Watershed

UR - http://www.scopus.com/inward/record.url?scp=0036383936&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036383936&partnerID=8YFLogxK

U2 - 10.1117/12.470102

DO - 10.1117/12.470102

M3 - Conference contribution

AN - SCOPUS:0036383936

VL - 4735

SP - 1

EP - 12

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Casasent, D.P.

A2 - Tescher, A.G.

T2 - Hybrid Image and Signal Processing VIII

Y2 - 4 April 2002 through 4 April 2002

ER -

Fast watershed aided by target detection

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this