Resumen en español

Currently one out of six couples present fertility problems, with 50% of the cases being due to the male. Until now, seminal fluid analysis is the only test that evaluates a male’s fertility potential. Among other parameters, sperm viability is manually assessed, which contributes to high data variability as a result of expert subjectivity and eye-fatigue. The purpose of the present study was to develop and experimentally validate a flexible, programmable and modular-based computational tool for digital image processing, identification and classification of human sperm in a semen sample. The regions were extracted using Fisher discriminant analysis and classification methods by cluster analysis and particularly the K-means technique. The results show 87.9% accuracy in identifying living and dead sperm, 93.4% effectiveness in detecting live sperm and 76% effectiveness in detecting dead sperm, from a set of 110 images obtained from 14 individuals, compared with manual analysis according to the procedures established by the World Health Organization. This computational tool contributes to the objective analysis of human sperm, becoming an alternative to expensive commercial systems for computer-assisted semen analysis