Categorizing sequences of laryngeal data for decision supportShow others and affiliations
2009 (English)In: Electrical and Control Technologies: Proceedings of the 4th international conference, ECT 2009 / [ed] A. Navickas (general editor), A. Sauhats, A. Virbalis, M. Ažubalis, V. Galvanauskas, A. Jonaitis, Kaunas: IFAC Committee of National Lithuanian Organisation , 2009, p. 99-102Conference paper, Published paper (Refereed)
Abstract [en]
This paper is concerned with kernel-based techniques forcategorizing laryngeal disorders based on information extracted fromsequences of laryngeal colour images. The features used tocharacterize a laryngeal image are given by the kernel principalcomponents computed using the $N$-vector of the 3-D colourhistogram. The least squares support vector machine (LS-SVM) isdesigned for categorizing an image sequence into the healthy, nodular and diffuse classes. The kernel functionemployed by the SVM classifier is defined over a pair of matrices, rather than over a pair of vectors. An encouraging classificationperformance was obtained when testing the developed tools on datarecorded during routine laryngeal videostroboscopy.
Place, publisher, year, edition, pages
Kaunas: IFAC Committee of National Lithuanian Organisation , 2009. p. 99-102
Series
Electrical and Control Technologies, ISSN 1822-5934 ; 2009
Keywords [en]
Larynx pathology, Image sequence, Classification, Support vector machine
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:hh:diva-108ISI: 000280250900021Scopus ID: 2-s2.0-84941695841OAI: oai:DiVA.org:hh-108DiVA, id: diva2:236173
Conference
Electrical and Control Technologies: proceedings of the 4th international conference, ECT 2009, May 7 - 8, Kaunas, Lithuania
2009-09-212009-09-212020-01-29Bibliographically approved