Spermatozoa detection, counting and tracking in video streams to detect asthenozoospermia

A semen analysis evaluates certain characteristics of a male´s semen and the sperm contained in the semen. The chance of pregnancy will be reduced, if more than 50 percent of a man´s sperm lack movement. Assessing the ability of sperm to move forward through the cervix into the fallopian tubes is a widely used measure of male infertility. Since the examination is done by a person through a microscope, a fairly simple system is used for classifying the spermatozoa. This paper proposes a technique to evaluate the motility of human spermatozoon which includes moving object detection, tracking and behavioral analysis. The objective is to measure the speed and quality of movement by tracking video clips of individual sperm cells. The approach chosen was frame differencing on consecutive frames, which identifies moving objects from the portion of a video frame that differs significantly from the previous frame. This method has less computation complexity, high recognition rate and a faster processing speed.