Extended power-based aggregation of distance functions and application in image segmentation

Marija Delić, Ljubo Nedović, E. Pap

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we psropose a novel method for construction of a distance function and demonstrate its application in image segmentation. In algorithms for image segmentation, distance functions represent a criterion which divides pixels into groups of segments. We introduce two extended aggregation functions, extended powers productand extended weighted arithmetic mean of powers. Their relevant properties are examined, as well as certain resulting properties of distance functions, which are constructed by an application of mentioned aggregation functions. In addition, one pixel descriptor, which is motivated by Local Binary Patternfamily of descriptors (LBPs), is introduced and discussed. In the experimental section, we present an application of the introduced extended aggregation functions and descriptor, by a construction of a new distance function, used in Fuzzy c-Means Clustering Algorithm (FCM) for image segmentation.

Original languageEnglish
Pages (from-to)155-173
Number of pages19
JournalInformation Sciences
Volume494
DOIs
Publication statusPublished - Aug 1 2019

Fingerprint

Distance Function
Image segmentation
Aggregation Function
Image Segmentation
Aggregation
Agglomeration
Descriptors
Pixel
Fuzzy C-means Clustering
Clustering Algorithm
Divides
Pixels
Binary
Distance function
Clustering algorithms
Demonstrate

Keywords

  • Distance function
  • Extended aggregation function
  • Fuzzy c-Means algorithm
  • Image segmentation
  • Local binary pattern
  • Metrics

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

Extended power-based aggregation of distance functions and application in image segmentation. / Delić, Marija; Nedović, Ljubo; Pap, E.

In: Information Sciences, Vol. 494, 01.08.2019, p. 155-173.

Research output: Contribution to journalArticle

@article{9f6db4c0c35f41c8a3362c8f933fe5cb,
title = "Extended power-based aggregation of distance functions and application in image segmentation",
abstract = "In this paper, we psropose a novel method for construction of a distance function and demonstrate its application in image segmentation. In algorithms for image segmentation, distance functions represent a criterion which divides pixels into groups of segments. We introduce two extended aggregation functions, extended powers productand extended weighted arithmetic mean of powers. Their relevant properties are examined, as well as certain resulting properties of distance functions, which are constructed by an application of mentioned aggregation functions. In addition, one pixel descriptor, which is motivated by Local Binary Patternfamily of descriptors (LBPs), is introduced and discussed. In the experimental section, we present an application of the introduced extended aggregation functions and descriptor, by a construction of a new distance function, used in Fuzzy c-Means Clustering Algorithm (FCM) for image segmentation.",
keywords = "Distance function, Extended aggregation function, Fuzzy c-Means algorithm, Image segmentation, Local binary pattern, Metrics",
author = "Marija Delić and Ljubo Nedović and E. Pap",
year = "2019",
month = "8",
day = "1",
doi = "10.1016/j.ins.2019.04.053",
language = "English",
volume = "494",
pages = "155--173",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Extended power-based aggregation of distance functions and application in image segmentation

AU - Delić, Marija

AU - Nedović, Ljubo

AU - Pap, E.

PY - 2019/8/1

Y1 - 2019/8/1

N2 - In this paper, we psropose a novel method for construction of a distance function and demonstrate its application in image segmentation. In algorithms for image segmentation, distance functions represent a criterion which divides pixels into groups of segments. We introduce two extended aggregation functions, extended powers productand extended weighted arithmetic mean of powers. Their relevant properties are examined, as well as certain resulting properties of distance functions, which are constructed by an application of mentioned aggregation functions. In addition, one pixel descriptor, which is motivated by Local Binary Patternfamily of descriptors (LBPs), is introduced and discussed. In the experimental section, we present an application of the introduced extended aggregation functions and descriptor, by a construction of a new distance function, used in Fuzzy c-Means Clustering Algorithm (FCM) for image segmentation.

AB - In this paper, we psropose a novel method for construction of a distance function and demonstrate its application in image segmentation. In algorithms for image segmentation, distance functions represent a criterion which divides pixels into groups of segments. We introduce two extended aggregation functions, extended powers productand extended weighted arithmetic mean of powers. Their relevant properties are examined, as well as certain resulting properties of distance functions, which are constructed by an application of mentioned aggregation functions. In addition, one pixel descriptor, which is motivated by Local Binary Patternfamily of descriptors (LBPs), is introduced and discussed. In the experimental section, we present an application of the introduced extended aggregation functions and descriptor, by a construction of a new distance function, used in Fuzzy c-Means Clustering Algorithm (FCM) for image segmentation.

KW - Distance function

KW - Extended aggregation function

KW - Fuzzy c-Means algorithm

KW - Image segmentation

KW - Local binary pattern

KW - Metrics

UR - http://www.scopus.com/inward/record.url?scp=85064919965&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064919965&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2019.04.053

DO - 10.1016/j.ins.2019.04.053

M3 - Article

AN - SCOPUS:85064919965

VL - 494

SP - 155

EP - 173

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -