Evolutionary Multi-level Thresholding for Breast Thermogram Segmentation

Arti Tiwari, Kamanasish Bhattacharjee, Millie Pant, Jana Nowakova, Vaclav Snasel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

In the pre-processing of the digital thermograms, multi-level thresholding plays a crucial role in the segmentation of thermographic images for better clinical decision support. This paper attempts to optimize the multi-level thresholding method for thermographic image segmentation using Differential Evolution (DE) with the Otsu’s between class variance. We have compared the results of the proposed method with the other popular metaheuristics- PSO, GWO and WOA. We have applied the Wilcoxon rank-sum test for the performance evaluation.

Original languageEnglish
Title of host publicationAdvances in Intelligent Networking and Collaborative Systems - The 13th International Conference on Intelligent Networking and Collaborative Systems, INCoS-2021
EditorsLeonard Barolli, Hsing-Chung Chen, Tomoya Enokido
PublisherSpringer Science and Business Media Deutschland GmbH
Pages253-263
Number of pages11
ISBN (Print)9783030849092
DOIs
StatePublished - 1 Jan 2022
Externally publishedYes
Event13th International Conference on Intelligent Networking and Collaborative Systems, INCoS 2021 - Taichung, Taiwan, Province of China
Duration: 1 Sep 20213 Sep 2021

Publication series

NameLecture Notes in Networks and Systems
Volume312
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference13th International Conference on Intelligent Networking and Collaborative Systems, INCoS 2021
Country/TerritoryTaiwan, Province of China
CityTaichung
Period1/09/213/09/21

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Evolutionary Multi-level Thresholding for Breast Thermogram Segmentation'. Together they form a unique fingerprint.

Cite this