Applicability of fuzzy clustering for the identification of upwelling areas on sea surface temperature images

Susana Maria dos Santos Nascimento M. de Almeida, Hugo Casimiro, Fátima M. Sousa, Dmitri Boutov

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

6 Citations (Scopus)

Abstract

This work explores the applicability of fuzzy clustering methods to the segmentation of sea surface temperature (SST) images for the automatic identification of upwelling areas in the coastal ocean of Portugal. This has been done by exploring the fuzzy c-means algorithm. Visualization of fuzzy c-partitions is achieved by means of color mapping. Selection of the best c-partition that represents the upwelling stages is done using the Xie- Beni validation index. Besides, by measuring the matching rate between a c-partition and 'ground truth' image whose upwelling area had been manually contoured by oceanographers, one evaluates how closely the algorithm reproduces the shape of the upwelling areas.

Original languageEnglish
Title of host publicationProceedings of the 2005 UK Workshop on Computational Intelligence
Subtitle of host publicationUK Ci 2005: London, UK 5-7 September 2005
EditorsBoris Mirkin, George Magoulas
Place of PublicationBirkbeck
PublisherUniversity of London
Pages143-148
Number of pages6
Publication statusPublished - 2005
Event2005 UK Workshop on Computational Intelligence, UKCI 2005 - London, United Kingdom
Duration: 5 Sept 20057 Sept 2005

Conference

Conference2005 UK Workshop on Computational Intelligence, UKCI 2005
Country/TerritoryUnited Kingdom
CityLondon
Period5/09/057/09/05

Fingerprint

Dive into the research topics of 'Applicability of fuzzy clustering for the identification of upwelling areas on sea surface temperature images'. Together they form a unique fingerprint.

Cite this