AUTOMATIC ANALYSIS OF IMAGES OF THE ANTERIOR CHAMBER OF AN EYE

摘要

An eye image including an image of the region containing the intersection of the cornea and iris is processed to identify whether it contains two proximate lines, since it is experimentally observed that this is characteristic of a non-zero value of the iridocorneal angle. The method includes an edge detection step, and then a method of determining whether edges have been detected which comprise these two proximate lines. The lines may be required to meet pre-known criteria, which are obtained from knowledge about the structure of the eye. In this way, it is possible to reduce the influence of other spurious edges in the eye image. The invention makes possible a precise, efficient and automatic system to grade the angle, which in turn makes it possible to provide large-scale clinical use.