LVQ acrosome integrity assessment of boar sperm cells

Nicolai Petkov*, Enrique Alegre, Michael Biehl, Lidia Sánchez

*Bijbehorende auteur voor dit werk

OnderzoeksoutputAcademicpeer review

11 Citaten (Scopus)
75 Downloads (Pure)

Samenvatting

We consider images of boar spermatozoa obtained with an optical phase-contrast microscope. Our goal is to automatically classify single sperm cells as acrosome-intact (class 1) or acrosome-reacted (class 2). Such classification is important for the estimation of the fertilization potential of a sperm sample for artificial insemination. We segment the sperm heads and compute a feature vector for each head. As a feature vector we use the gradient magnitude along the contour of the sperm head. We apply learning vector quantization (LVQ) to the feature vectors obtained for 152 heads that were visually inspected and classified by a veterinary expert. A simple LVQ system with only three prototypes (two for class I and one for class 2) allows us to classify cells with equal training and test errors of 0.165. This is considered to be sufficient for semen quality control in an artificial insemination center.

Originele taal-2English
TitelCOMPUTATIONAL MODELLING OF OBJECTS REPRESENTED IN IMAGES: FUNDAMENTALS, METHODS AND APPLICATIONS
RedacteurenJMRS Tavares, RMN Jorge
Plaats van productieLONDON
UitgeverijTaylor & Francis Group
Pagina's337-342
Aantal pagina's6
ISBN van geprinte versie978-0-415-43349-5
StatusPublished - 2007
EvenementInternational Symposium on Computational Modelling of Objects Represented in Images (CompIMAGE 2006) - , Portugal
Duur: 20-okt-200621-okt-2006

Publicatie series

NaamProceedings and Monographs in Engineering, Water and Earth Sciences
UitgeverijTAYLOR & FRANCIS LTD

Other

OtherInternational Symposium on Computational Modelling of Objects Represented in Images (CompIMAGE 2006)
Land/RegioPortugal
Periode20/10/200621/10/2006

Citeer dit