Bull sperm motility measurement using improved matching-based algorithm and ellipse detection

Abstract

Based on Indonesian standard in measuring bull sperm quality, motility is the most important parameter. Sperm motility can be measured manually by medical veterinarian or using Computer Aided Sperm Analysis (CASA) system. Measuring bull sperm motility manually is the most popular method nevertheless it is often subjective and high variability. CASA gives consistent results, hence it is an expensive system. Therefore an alternative method is required. In this paper, we proposed a method to measure bull sperm motility using improved matching-based algorithm and ellipse detection. The image samples were taken using multimedia microscope. Compared with the manual assessment by medical veterinarians, the proposed method gives the smallest average margin of 2.3% on 60 fps videos and the largest of 3.5% in the videos with 30 fps frame rate which surpassed the previous method results.