Bidirectional labeling and registration scheme for grayscale image segmentation

Lei Ma, Xiao Ping Zhang, Jennie Si, Glen P. Abousleman

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, we introduce a new image segmentation scheme that is based on bidirectional labeling and registration and prove that its segmentation performance is equivalent to that of the conventional watershed segmentation algorithm. The proposed bidirectional labeling and registration scheme, which we refer to as bidirectional labeling and registration scheme (BIDS), involves only linear scans of image pixels. It uses one-dimensional operations rather than the queues that are used in traditional segmentation algorithms, which are two-dimensional problems. BIDS also provides unique labels for individual homogeneous regions. In addition to achieving the same segmentation results, BIDS is four times less computationally complex than the conventional watershed by immersion technique.

Original languageEnglish (US)
Pages (from-to)2073-2081
Number of pages9
JournalIEEE Transactions on Image Processing
Volume14
Issue number12
DOIs
StatePublished - Dec 2005

Fingerprint

Image segmentation
Image Segmentation
Labeling
Registration
Segmentation
Watersheds
Labels
Pixels
Immersion
Queue
Pixel

Keywords

  • Bidirectional labeling
  • Catchment basin
  • Gradient map
  • Image segmentation
  • Region merge
  • Region registration
  • Watershed

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Graphics and Computer-Aided Design
  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition

Cite this

Bidirectional labeling and registration scheme for grayscale image segmentation. / Ma, Lei; Zhang, Xiao Ping; Si, Jennie; Abousleman, Glen P.

In: IEEE Transactions on Image Processing, Vol. 14, No. 12, 12.2005, p. 2073-2081.

Research output: Contribution to journalArticle

Ma, Lei ; Zhang, Xiao Ping ; Si, Jennie ; Abousleman, Glen P. / Bidirectional labeling and registration scheme for grayscale image segmentation. In: IEEE Transactions on Image Processing. 2005 ; Vol. 14, No. 12. pp. 2073-2081.
@article{f791896a4e72450ebc0d3434f17b404a,
title = "Bidirectional labeling and registration scheme for grayscale image segmentation",
abstract = "In this paper, we introduce a new image segmentation scheme that is based on bidirectional labeling and registration and prove that its segmentation performance is equivalent to that of the conventional watershed segmentation algorithm. The proposed bidirectional labeling and registration scheme, which we refer to as bidirectional labeling and registration scheme (BIDS), involves only linear scans of image pixels. It uses one-dimensional operations rather than the queues that are used in traditional segmentation algorithms, which are two-dimensional problems. BIDS also provides unique labels for individual homogeneous regions. In addition to achieving the same segmentation results, BIDS is four times less computationally complex than the conventional watershed by immersion technique.",
keywords = "Bidirectional labeling, Catchment basin, Gradient map, Image segmentation, Region merge, Region registration, Watershed",
author = "Lei Ma and Zhang, {Xiao Ping} and Jennie Si and Abousleman, {Glen P.}",
year = "2005",
month = "12",
doi = "10.1109/TIP.2005.857277",
language = "English (US)",
volume = "14",
pages = "2073--2081",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "12",

}

TY - JOUR

T1 - Bidirectional labeling and registration scheme for grayscale image segmentation

AU - Ma, Lei

AU - Zhang, Xiao Ping

AU - Si, Jennie

AU - Abousleman, Glen P.

PY - 2005/12

Y1 - 2005/12

N2 - In this paper, we introduce a new image segmentation scheme that is based on bidirectional labeling and registration and prove that its segmentation performance is equivalent to that of the conventional watershed segmentation algorithm. The proposed bidirectional labeling and registration scheme, which we refer to as bidirectional labeling and registration scheme (BIDS), involves only linear scans of image pixels. It uses one-dimensional operations rather than the queues that are used in traditional segmentation algorithms, which are two-dimensional problems. BIDS also provides unique labels for individual homogeneous regions. In addition to achieving the same segmentation results, BIDS is four times less computationally complex than the conventional watershed by immersion technique.

AB - In this paper, we introduce a new image segmentation scheme that is based on bidirectional labeling and registration and prove that its segmentation performance is equivalent to that of the conventional watershed segmentation algorithm. The proposed bidirectional labeling and registration scheme, which we refer to as bidirectional labeling and registration scheme (BIDS), involves only linear scans of image pixels. It uses one-dimensional operations rather than the queues that are used in traditional segmentation algorithms, which are two-dimensional problems. BIDS also provides unique labels for individual homogeneous regions. In addition to achieving the same segmentation results, BIDS is four times less computationally complex than the conventional watershed by immersion technique.

KW - Bidirectional labeling

KW - Catchment basin

KW - Gradient map

KW - Image segmentation

KW - Region merge

KW - Region registration

KW - Watershed

UR - http://www.scopus.com/inward/record.url?scp=28844440476&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=28844440476&partnerID=8YFLogxK

U2 - 10.1109/TIP.2005.857277

DO - 10.1109/TIP.2005.857277

M3 - Article

VL - 14

SP - 2073

EP - 2081

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 12

ER -