Classification of human parasite eggs based on enhanced multitexton histogram

Roxana Flores Quispe, Raquel Esperanza Patino Escarcina, Yuber Elmer Velazco Paredes, Cesar A. Beltran Castanon

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

4 Scopus citations

Abstract

The Content-based image retrieval (CBIR) systems and their application in different areas of development, are current research topics, for that reason in this study content-based image retrieval is applied to classificate eight different human parasite eggs: Ascarias, Uncinarias, Trichuris, Dyphillobothrium-Pacificum, Taenia-Solium, Fasciola Hepática and Enterobius-Vermicularis, which are into the class of Helminthes, from their microscopic images. This proposed system includes two stages. In first stage, a feature extraction mechanism that is based on multitexton histogram descriptor (MTH) which has been improved and called 'Enhanced MTH'. In second stage, an CBIR system has been implemented in orden to classificate the differents microscopic images to identify their correct species. Finally, simulation result shows overall success rates of 92,16% in the classification.

Original languageEnglish
Title of host publication2014 IEEE Colombian Conference on Communications and Computing, COLCOM 2014 - Conference Proceedings
PublisherIEEE Computer Society
ISBN (Print)9781479943401
DOIs
StatePublished - 2014
Externally publishedYes
Event2014 IEEE Colombian Conference on Communications and Computing, COLCOM 2014 - Bogota, Colombia
Duration: 4 Jun 20146 Jun 2014

Publication series

Name2014 IEEE Colombian Conference on Communications and Computing, COLCOM 2014 - Conference Proceedings

Conference

Conference2014 IEEE Colombian Conference on Communications and Computing, COLCOM 2014
Country/TerritoryColombia
CityBogota
Period4/06/146/06/14

Keywords

  • CBIR
  • Human Parasite Eggs
  • Multitexton Histogram descriptor

Fingerprint

Dive into the research topics of 'Classification of human parasite eggs based on enhanced multitexton histogram'. Together they form a unique fingerprint.

Cite this