Publications
2012
1.
González-Castro, Víctor; Alegre, Enrique; Olivera, Óscar García-Olalla; García-Ordás, Diego; García-Ordás, María Teresa; Fernández-Robles, Laura
Curvelet-based texture description to classify intact and damaged boar spermatozoa Artículo de revista
En: Image Analysis and Recognition: 9th International Conference, ICIAR 2012, Aveiro, Portugal, June 25-27, 2012. Proceedings, Part II 9, pp. 448–455, 2012, (Publisher: Springer Berlin Heidelberg).
Resumen | Enlaces | BibTeX | Etiquetas: Acrosome Status, Automation in Veterinary Diagnostics, Boar Sperm Analysis, Curvelet Transform, texture descriptors
@article{gonzalez-castro_curvelet-based_2012,
title = {Curvelet-based texture description to classify intact and damaged boar spermatozoa},
author = {Víctor González-Castro and Enrique Alegre and Óscar García-Olalla Olivera and Diego García-Ordás and María Teresa García-Ordás and Laura Fernández-Robles},
url = {https://link.springer.com/chapter/10.1007/978-3-642-31298-4_53},
year = {2012},
date = {2012-01-01},
journal = {Image Analysis and Recognition: 9th International Conference, ICIAR 2012, Aveiro, Portugal, June 25-27, 2012. Proceedings, Part II 9},
pages = {448–455},
abstract = {This paper proposes a new method for assessing boar sperm head images based on texture descriptors derived from the Curvelet Transform, aiming to automate acrosome status detection. Compared to other methods using Wavelet Transform and moments-based descriptors, the Curvelet-based texture descriptors outperformed the others, achieving a 97% hit rate and an area under the ROC curve of 0.99.},
note = {Publisher: Springer Berlin Heidelberg},
keywords = {Acrosome Status, Automation in Veterinary Diagnostics, Boar Sperm Analysis, Curvelet Transform, texture descriptors},
pubstate = {published},
tppubtype = {article}
}
This paper proposes a new method for assessing boar sperm head images based on texture descriptors derived from the Curvelet Transform, aiming to automate acrosome status detection. Compared to other methods using Wavelet Transform and moments-based descriptors, the Curvelet-based texture descriptors outperformed the others, achieving a 97% hit rate and an area under the ROC curve of 0.99.