Publications

@article{gonzalez-castro_adaptive_2014,

title = {Adaptive texture description and estimation of the class prior probabilities for seminal quality control},

author = {Víctor González-Castro},

url = {https://www.raco.cat/index.php/ELCVIA/article/view/281622},

year  = {2014},

date = {2014-01-01},

journal = {ELCVIA: electronic letters on computer vision and image analysis},

volume = {13},

number = {2},

pages = {19–21},

abstract = {Semen quality assessment is essential in artificial insemination for both humans and animals. In livestock farming, high-quality semen samples are crucial for successful fertilization, requiring strict quality control. Currently, sperm vitality and acrosome integrity are assessed manually, which is costly and prone to human errors. This research proposes an automated system based on image processing and machine learning to estimate the proportion of dead spermatozoa and damaged acrosomes using an affordable phase contrast microscope. New intelligent segmentation techniques and adaptive texture description methods have been developed and evaluated to improve automatic boar semen quality estimation.},

keywords = {artificial insemination, image processing, machine learning, semen quality},

pubstate = {published},

tppubtype = {article}

}

@article{alegre_automatic_2008,

title = {Automatic classification of the acrosome status of boar spermatozoa using digital image processing and LVQ},

author = {Enrique Alegre and Michael Biehl and Nicolai Petkov and Lidia Sánchez-González},

url = {https://www.sciencedirect.com/science/article/pii/S0010482508000103},

year  = {2008},

date = {2008-01-01},

urldate = {2008-01-01},

journal = {Computers in Biology and Medicine},

volume = {38},

number = {4},

pages = {461–468},

abstract = {This paper presents an automatic method for classifying boar sperm cells as acrosome-intact or acrosome-damaged using phase-contrast microscopy images. Sperm heads are segmented, and feature vectors based on gradient magnitude along the contour are extracted. Learning Vector Quantization (LVQ) is applied to classify 320 labeled sperm heads, achieving a 6.8% test error, which is sufficient for semen quality control in artificial insemination.},

note = {Publisher: Pergamon},

keywords = {artificial insemination, machine learning, phase-contrast microscopy, sperm classification},

pubstate = {published},

tppubtype = {article}

}