Comparison of Visual Feature Extraction Methods of Sperms in Semen Microscopic Videos.

The morphology, number, density and sperm motility of male sperm are important indicators to measure male reproductive health. In microscopic videos, visual feature plays a fundamental role in sperm recognition and classification. For this purpose, we compare the effectiveness of different visual features of sperms in recognition and classification with four different classifiers. In the experiment, we use a sperm microscopic video data set to evaluate the visual feature, including two types of 1374 sperms, and obtain the evaluation of different visual features.