Publications:Towards video laryngostroboscopy-based automated screening for laryngeal disorders
Property "Publisher" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user.
| Title | Towards video laryngostroboscopy-based automated screening for laryngeal disorders |
|---|---|
| Author | |
| Year | 2009 |
| PublicationType | Conference Paper |
| Journal | |
| HostPublication | Proceedings of the 6th International Conference “Models and Analysis of Vocal Emissions for Biomedical Applications”, MAVEBA 2009 |
| Conference | 6th International Conference “Models and Analysis of Vocal Emissions for Biomedical Applications”, MAVEBA 2009, December 14-16, Firenze, Italy |
| DOI | |
| Diva url | http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:284996 |
| Abstract | This paper is concerned with kernel-based techniques for automatedcategorization of laryngeal colour image sequences obtained by videolaryngostroboscopy. Features used to characterize a laryngeal imageare given by the kernel principal components computed using the$N$-vector of the 3-D colour histogram. The least squares supportvector machine (LS-SVM) is designed for categorizing an imagesequence (video) into the healthy, cancerous and noncancerous classes. The kernel function employed by theLS-SVM is defined over a pair of matrices, rather than over a pairof vectors. The classification accuracy of over 85% was obtainedwhen testing the developed tools on data recorded during routinelaryngeal videostroboscopy. |
