Parameter-free hierarchical image segmentation

S M Abdullah, Peter Tischer, Sudanthi Wijewickrema, Andrew Paplinski

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

Abstract

Images typically have many levels of detail and the suitability of a segmentation depends on application requirements. Thus, it is imperative that the user/application be given the option to select the 'optimal' segmentation that captures the desired level of detail from a set of segmentations. This paper presents a hierarchical image segmentation algorithm that offers this option using the concept of minimum spanning trees. It converts an input image into a tree structure from which a hierarchy of segmentations is obtained through a process of merging. No parameters are used in this process and thus the proposed algorithm can be used on any segmentation dataset as is. The levels are calculated in one pass of the minimum spanning tree and as such, no iterative merging is required. This provides the user with a quick way of segment visualisation. Evaluation results on two popular segmentation datasets show that the algorithm provides competitive results in comparison to other segmentation algorithms.

Original languageEnglish
Title of host publication2017 IEEE Visual Communications and Image Processing (VCIP)
EditorsEckehard Steinbach, Weisi Lin, Carlos Busso, Siwei Ma
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages4
ISBN (Electronic)9781538604625
ISBN (Print)9781538604632
DOIs
Publication statusPublished - 2017
EventSPIE International Conference on Visual Communications and Image Processing 2017 - St Petersburg, United States of America
Duration: 10 Dec 201713 Dec 2017
http://www.vcip2017.org/

Conference

ConferenceSPIE International Conference on Visual Communications and Image Processing 2017
Abbreviated titleVCIP 2017
CountryUnited States of America
CitySt Petersburg
Period10/12/1713/12/17
OtherIEEE Visual Communications and Image Processing
Internet address

Keywords

  • hierarchical
  • MST
  • parameter-free
  • segment visualiser
  • segmentation

Cite this

Abdullah, S. M., Tischer, P., Wijewickrema, S., & Paplinski, A. (2017). Parameter-free hierarchical image segmentation. In E. Steinbach, W. Lin, C. Busso, & S. Ma (Eds.), 2017 IEEE Visual Communications and Image Processing (VCIP) Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/VCIP.2017.8305030
Abdullah, S M ; Tischer, Peter ; Wijewickrema, Sudanthi ; Paplinski, Andrew. / Parameter-free hierarchical image segmentation. 2017 IEEE Visual Communications and Image Processing (VCIP). editor / Eckehard Steinbach ; Weisi Lin ; Carlos Busso ; Siwei Ma. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017.
@inproceedings{8aa1156218b0450b88418688ae68347a,
title = "Parameter-free hierarchical image segmentation",
abstract = "Images typically have many levels of detail and the suitability of a segmentation depends on application requirements. Thus, it is imperative that the user/application be given the option to select the 'optimal' segmentation that captures the desired level of detail from a set of segmentations. This paper presents a hierarchical image segmentation algorithm that offers this option using the concept of minimum spanning trees. It converts an input image into a tree structure from which a hierarchy of segmentations is obtained through a process of merging. No parameters are used in this process and thus the proposed algorithm can be used on any segmentation dataset as is. The levels are calculated in one pass of the minimum spanning tree and as such, no iterative merging is required. This provides the user with a quick way of segment visualisation. Evaluation results on two popular segmentation datasets show that the algorithm provides competitive results in comparison to other segmentation algorithms.",
keywords = "hierarchical, MST, parameter-free, segment visualiser, segmentation",
author = "Abdullah, {S M} and Peter Tischer and Sudanthi Wijewickrema and Andrew Paplinski",
year = "2017",
doi = "10.1109/VCIP.2017.8305030",
language = "English",
isbn = "9781538604632",
editor = "Steinbach, {Eckehard } and Lin, {Weisi } and Busso, {Carlos } and Siwei Ma",
booktitle = "2017 IEEE Visual Communications and Image Processing (VCIP)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Abdullah, SM, Tischer, P, Wijewickrema, S & Paplinski, A 2017, Parameter-free hierarchical image segmentation. in E Steinbach, W Lin, C Busso & S Ma (eds), 2017 IEEE Visual Communications and Image Processing (VCIP). IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, SPIE International Conference on Visual Communications and Image Processing 2017, St Petersburg, United States of America, 10/12/17. https://doi.org/10.1109/VCIP.2017.8305030

Parameter-free hierarchical image segmentation. / Abdullah, S M; Tischer, Peter; Wijewickrema, Sudanthi; Paplinski, Andrew.

2017 IEEE Visual Communications and Image Processing (VCIP). ed. / Eckehard Steinbach; Weisi Lin; Carlos Busso; Siwei Ma. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

TY - GEN

T1 - Parameter-free hierarchical image segmentation

AU - Abdullah, S M

AU - Tischer, Peter

AU - Wijewickrema, Sudanthi

AU - Paplinski, Andrew

PY - 2017

Y1 - 2017

N2 - Images typically have many levels of detail and the suitability of a segmentation depends on application requirements. Thus, it is imperative that the user/application be given the option to select the 'optimal' segmentation that captures the desired level of detail from a set of segmentations. This paper presents a hierarchical image segmentation algorithm that offers this option using the concept of minimum spanning trees. It converts an input image into a tree structure from which a hierarchy of segmentations is obtained through a process of merging. No parameters are used in this process and thus the proposed algorithm can be used on any segmentation dataset as is. The levels are calculated in one pass of the minimum spanning tree and as such, no iterative merging is required. This provides the user with a quick way of segment visualisation. Evaluation results on two popular segmentation datasets show that the algorithm provides competitive results in comparison to other segmentation algorithms.

AB - Images typically have many levels of detail and the suitability of a segmentation depends on application requirements. Thus, it is imperative that the user/application be given the option to select the 'optimal' segmentation that captures the desired level of detail from a set of segmentations. This paper presents a hierarchical image segmentation algorithm that offers this option using the concept of minimum spanning trees. It converts an input image into a tree structure from which a hierarchy of segmentations is obtained through a process of merging. No parameters are used in this process and thus the proposed algorithm can be used on any segmentation dataset as is. The levels are calculated in one pass of the minimum spanning tree and as such, no iterative merging is required. This provides the user with a quick way of segment visualisation. Evaluation results on two popular segmentation datasets show that the algorithm provides competitive results in comparison to other segmentation algorithms.

KW - hierarchical

KW - MST

KW - parameter-free

KW - segment visualiser

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=85050632796&partnerID=8YFLogxK

U2 - 10.1109/VCIP.2017.8305030

DO - 10.1109/VCIP.2017.8305030

M3 - Conference Paper

SN - 9781538604632

BT - 2017 IEEE Visual Communications and Image Processing (VCIP)

A2 - Steinbach, Eckehard

A2 - Lin, Weisi

A2 - Busso, Carlos

A2 - Ma, Siwei

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Abdullah SM, Tischer P, Wijewickrema S, Paplinski A. Parameter-free hierarchical image segmentation. In Steinbach E, Lin W, Busso C, Ma S, editors, 2017 IEEE Visual Communications and Image Processing (VCIP). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2017 https://doi.org/10.1109/VCIP.2017.8305030