Publications
2005
1.
Sánchez-González, Lidia; Petkov, Nicolai; Alegre, Enrique
Statistical approach to boar semen head classification based on intracellular intensity distribution Artículo de revista
En: International Conference on Computer Analysis of Images and Patterns, pp. 88–95, 2005, (Publisher: Springer Berlin Heidelberg Berlin, Heidelberg).
Resumen | Enlaces | BibTeX | Etiquetas: Digital Estimation, image processing, Sperm Capacitation, sperm classification, Veterinary Analysis
@article{sanchez-gonzalez_statistical_2005,
title = {Statistical approach to boar semen head classification based on intracellular intensity distribution},
author = {Lidia Sánchez-González and Nicolai Petkov and Enrique Alegre},
url = {https://link.springer.com/chapter/10.1007/11556121_12},
year = {2005},
date = {2005-01-01},
journal = {International Conference on Computer Analysis of Images and Patterns},
pages = {88–95},
abstract = {This technique estimates the fraction of boar sperm heads exhibiting a normal intracellular density pattern, as defined by veterinary experts. It offers a potential alternative to costly staining methods for sperm capacitation. The method involves training a model using images classified as normal, similar to normal, and abnormal. The deviation of each sperm head from the model is used to calculate a conditional probability, allowing for accurate estimation of normal sperm fractions, with an error below 0.25 in 89% of the test samples.},
note = {Publisher: Springer Berlin Heidelberg Berlin, Heidelberg},
keywords = {Digital Estimation, image processing, Sperm Capacitation, sperm classification, Veterinary Analysis},
pubstate = {published},
tppubtype = {article}
}
This technique estimates the fraction of boar sperm heads exhibiting a normal intracellular density pattern, as defined by veterinary experts. It offers a potential alternative to costly staining methods for sperm capacitation. The method involves training a model using images classified as normal, similar to normal, and abnormal. The deviation of each sperm head from the model is used to calculate a conditional probability, allowing for accurate estimation of normal sperm fractions, with an error below 0.25 in 89% of the test samples.