Automatic image segmentation by integrating color-edge extraction and seeded region growing

Jianping Fan, David K Y Yau, Ahmed Elmagarmid, Walid G. Aref

Research output: Contribution to journalArticle

433 Citations (Scopus)

Abstract

We propose a new automatic image segmentation method. Color edges in an image are first obtained automatically by combining an improved isotropic edge detector and a fast entropic thresholding technique. After the obtained color edges have provided the major geometric structures in an image, the centroids between these adjacent edge regions are taken as the initial seeds for seeded region growing (SRG). These seeds are then replaced by the centroids of the generated homogeneous image regions by incorporating the required additional pixels step by step. Moreover, the results of color-edge extraction and SRG are integrated to provide homogeneous image regions with accurate and closed boundaries. We also discuss the application of our image segmentation method to automatic face detection. Furthermore, semantic human objects are generated by a seeded region aggregation procedure which takes the detected faces as object seeds.

Original languageEnglish
Pages (from-to)1454-1466
Number of pages13
JournalIEEE Transactions on Image Processing
Volume10
Issue number10
DOIs
Publication statusPublished - 1 Oct 2001
Externally publishedYes

Fingerprint

Region Growing
Image segmentation
Image Segmentation
Color
Seed
Seeds
Centroid
Face recognition
Semantics
Face Detection
Geometric Structure
Agglomeration
Thresholding
Pixels
Detectors
Aggregation
Adjacent
Pixel
Detector
Face

Keywords

  • Edge detection
  • Face detection
  • Image segmentation
  • Seeded region growing (SRG)

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

Automatic image segmentation by integrating color-edge extraction and seeded region growing. / Fan, Jianping; Yau, David K Y; Elmagarmid, Ahmed; Aref, Walid G.

In: IEEE Transactions on Image Processing, Vol. 10, No. 10, 01.10.2001, p. 1454-1466.

Research output: Contribution to journalArticle

@article{3c3bf63dc5cc4af2a7b42e985bdafc98,
title = "Automatic image segmentation by integrating color-edge extraction and seeded region growing",
abstract = "We propose a new automatic image segmentation method. Color edges in an image are first obtained automatically by combining an improved isotropic edge detector and a fast entropic thresholding technique. After the obtained color edges have provided the major geometric structures in an image, the centroids between these adjacent edge regions are taken as the initial seeds for seeded region growing (SRG). These seeds are then replaced by the centroids of the generated homogeneous image regions by incorporating the required additional pixels step by step. Moreover, the results of color-edge extraction and SRG are integrated to provide homogeneous image regions with accurate and closed boundaries. We also discuss the application of our image segmentation method to automatic face detection. Furthermore, semantic human objects are generated by a seeded region aggregation procedure which takes the detected faces as object seeds.",
keywords = "Edge detection, Face detection, Image segmentation, Seeded region growing (SRG)",
author = "Jianping Fan and Yau, {David K Y} and Ahmed Elmagarmid and Aref, {Walid G.}",
year = "2001",
month = "10",
day = "1",
doi = "10.1109/83.951532",
language = "English",
volume = "10",
pages = "1454--1466",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "10",

}

TY - JOUR

T1 - Automatic image segmentation by integrating color-edge extraction and seeded region growing

AU - Fan, Jianping

AU - Yau, David K Y

AU - Elmagarmid, Ahmed

AU - Aref, Walid G.

PY - 2001/10/1

Y1 - 2001/10/1

N2 - We propose a new automatic image segmentation method. Color edges in an image are first obtained automatically by combining an improved isotropic edge detector and a fast entropic thresholding technique. After the obtained color edges have provided the major geometric structures in an image, the centroids between these adjacent edge regions are taken as the initial seeds for seeded region growing (SRG). These seeds are then replaced by the centroids of the generated homogeneous image regions by incorporating the required additional pixels step by step. Moreover, the results of color-edge extraction and SRG are integrated to provide homogeneous image regions with accurate and closed boundaries. We also discuss the application of our image segmentation method to automatic face detection. Furthermore, semantic human objects are generated by a seeded region aggregation procedure which takes the detected faces as object seeds.

AB - We propose a new automatic image segmentation method. Color edges in an image are first obtained automatically by combining an improved isotropic edge detector and a fast entropic thresholding technique. After the obtained color edges have provided the major geometric structures in an image, the centroids between these adjacent edge regions are taken as the initial seeds for seeded region growing (SRG). These seeds are then replaced by the centroids of the generated homogeneous image regions by incorporating the required additional pixels step by step. Moreover, the results of color-edge extraction and SRG are integrated to provide homogeneous image regions with accurate and closed boundaries. We also discuss the application of our image segmentation method to automatic face detection. Furthermore, semantic human objects are generated by a seeded region aggregation procedure which takes the detected faces as object seeds.

KW - Edge detection

KW - Face detection

KW - Image segmentation

KW - Seeded region growing (SRG)

UR - http://www.scopus.com/inward/record.url?scp=0035474775&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035474775&partnerID=8YFLogxK

U2 - 10.1109/83.951532

DO - 10.1109/83.951532

M3 - Article

VL - 10

SP - 1454

EP - 1466

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 10

ER -