Computer Aided Motile Sperm Counting

Abstract

The rapid and irregular motion of semen cells makes the counting process of semen difficult in the visual assessment. Therefore, computer based techniques are necessary to evaluate the tests with more accurately. In this paper, an alternative way to the visual assessment technique in spermiogram tests is presented. Analyses are performed on the recorded microscope video images by computer, automatically. As a first step in the study, Mean Filter is utilized for the background subtraction. Afterwards, foreground models were formed by Frame Differencing technique, which is taking pixel-based intensity differences of current frame and background model. Moving semen cells stated on the foreground were labeled using blob analysis. The results of the presented study are compared with the result obtained by SQA CASA system. Proposed method is validated by the correlation between results (0.9942). In addition, the proposed system can analyze samples with low semen density where the CASA systems are unable to evaluate.