Automatic marker detection for blob images

António Dos Anjos; Hamid Reza Shahbazkia

doi:10.1109/WACV.2009.5403115

Automatic marker detection for blob images

António Dos Anjos^*, Hamid Reza Shahbazkia

^*Corresponding author for this work

Department of Computer Science

University of Algarve

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (Non-Journal item)

1 Citation (Scopus)

Abstract

The direct application of the Watershed Transform to images with moderate contrast between foreground and background often produces segmentation where the segmented areas will still have a lot of background included. One typical example of this is the segmentation of blob images. To narrow the border of these areas, the Watershed Transform may be applied to the gradient magnitude of the image, but it results in over-segmentation. Marker Controlled Watershed Transform is one of the best approaches for the segmentation of this kind of images, however, in most cases it is impracticable to manually select the markers. This paper presents a technique that allows the automatic detection of markers on blob images and subsequent segmentation.

Original language	English
Title of host publication	2009 Workshop on Applications of Computer Vision, WACV 2009
Publisher	IEEE Press
ISBN (Print)	9781424454976
DOIs	https://doi.org/10.1109/WACV.2009.5403115
Publication status	Published - 2009
Event	2009 Workshop on Applications of Computer Vision, WACV 2009 - Snowbird, UT, United States of America Duration: 07 Dec 2009 → 08 Dec 2009

Conference

Conference	2009 Workshop on Applications of Computer Vision, WACV 2009
Country/Territory	United States of America
City	Snowbird, UT
Period	07 Dec 2009 → 08 Dec 2009

Access to Document

10.1109/WACV.2009.5403115

Permanent link

Persistent link

Cite this

@inproceedings{64de8aff7da24da98c819a8a58bc3108,

title = "Automatic marker detection for blob images",

abstract = "The direct application of the Watershed Transform to images with moderate contrast between foreground and background often produces segmentation where the segmented areas will still have a lot of background included. One typical example of this is the segmentation of blob images. To narrow the border of these areas, the Watershed Transform may be applied to the gradient magnitude of the image, but it results in over-segmentation. Marker Controlled Watershed Transform is one of the best approaches for the segmentation of this kind of images, however, in most cases it is impracticable to manually select the markers. This paper presents a technique that allows the automatic detection of markers on blob images and subsequent segmentation.",

author = "{Dos Anjos}, Ant{\'o}nio and Shahbazkia, {Hamid Reza}",

year = "2009",

doi = "10.1109/WACV.2009.5403115",

language = "English",

isbn = "9781424454976",

booktitle = "2009 Workshop on Applications of Computer Vision, WACV 2009",

publisher = "IEEE Press",

address = "United States of America",

note = "2009 Workshop on Applications of Computer Vision, WACV 2009 ; Conference date: 07-12-2009 Through 08-12-2009",

}

TY - GEN

T1 - Automatic marker detection for blob images

AU - Dos Anjos, António

AU - Shahbazkia, Hamid Reza

PY - 2009

Y1 - 2009

N2 - The direct application of the Watershed Transform to images with moderate contrast between foreground and background often produces segmentation where the segmented areas will still have a lot of background included. One typical example of this is the segmentation of blob images. To narrow the border of these areas, the Watershed Transform may be applied to the gradient magnitude of the image, but it results in over-segmentation. Marker Controlled Watershed Transform is one of the best approaches for the segmentation of this kind of images, however, in most cases it is impracticable to manually select the markers. This paper presents a technique that allows the automatic detection of markers on blob images and subsequent segmentation.

AB - The direct application of the Watershed Transform to images with moderate contrast between foreground and background often produces segmentation where the segmented areas will still have a lot of background included. One typical example of this is the segmentation of blob images. To narrow the border of these areas, the Watershed Transform may be applied to the gradient magnitude of the image, but it results in over-segmentation. Marker Controlled Watershed Transform is one of the best approaches for the segmentation of this kind of images, however, in most cases it is impracticable to manually select the markers. This paper presents a technique that allows the automatic detection of markers on blob images and subsequent segmentation.

UR - http://www.scopus.com/inward/record.url?scp=77951182645&partnerID=8YFLogxK

U2 - 10.1109/WACV.2009.5403115

DO - 10.1109/WACV.2009.5403115

M3 - Conference Proceeding (Non-Journal item)

AN - SCOPUS:77951182645

SN - 9781424454976

BT - 2009 Workshop on Applications of Computer Vision, WACV 2009

PB - IEEE Press

T2 - 2009 Workshop on Applications of Computer Vision, WACV 2009

Y2 - 7 December 2009 through 8 December 2009

ER -

Automatic marker detection for blob images

Abstract

Conference

Access to Document

Permanent link

Other files and links

Fingerprint

Cite this