A new method based on the Hough transform has been used for the quanti
tative estimation of the morphological characteristics of the sperm. I
mages of the sperms were acquired into the digital format using the op
tical microscope, CCD camera, and frame grabber. For each sperm in the
image, the region of interest for the segmentation of the sperm head
was selected using the density difference between the sperm head and b
ackground. The boundary of the sperm head was approximated with an ell
ipse and represented by five parameters. These five parameters represe
nting an ellipse have been investigated by applying the Hough transfor
m strategically. During the searching procedure using the Hough transf
orm, we restricted the searching volume minimally and moved the next s
earching volume to the direction showing the steepest gradient of the
estimation error. Also, we increased the parameter resolution from the
three pixel distance to the one pixel distance. For the tested images
, head boundaries of the sperms were estimated with an error of 1/2 pi
xel distance, and morphological parameters were calculated by the equa
tions without further image processing. This new method separates sper
m head based on the geometrical characteristic of the sperm and calcul
ates morphological parameters simply from the derived boundary.