EFFECTIVE DETECTION OF NUCLEUS IN CYTODIAGNOSIS BY EMPLOYING COMBINATORIAL FUZZY HOUGH TRANSFORM

Hough transform is an effective method for line detection in a digital image. However, the conventional Hough transform can not be applied w ell enough for an image corrupted by heavy noise. This paper describes a combinatorial fuzzy Hough transform, which enables a detection of n ot only a blurred line, but also a segment of a line in a very noisy i mage. It is then extended in order that it can further detect a blurre d circle. The effectiveness of the present method has been confirmed b y applying it to an actual microphotograph for cytodiagnosis. It can d etect the nuclei in a cell cluster in a very noisy medical image.