Affiliations: Department of Control Engineering and Science, Kyushu Institute of Technology, Iizuka, Fukuoka 820, Japan | Olympus Optical Co., Ltd., Monolith 3-1, Nishi-Shinjuku 2, Shinjuku, Tokyo, Japan
Note: [] The author is also with the Fuzzy Logic Systems Institute (FLSI), Iizuka, Fukuoka 820, Japan.
Note: [] The author is also with the Fuzzy Logic Systems Institute (FLSI), Iizuka, Fukuoka 820, Japan.
Note: [] This research was done when the author was in the graduate school of Computer Science and Systems Engineering, Kyushu Institute of Technology.
Abstract: Hough transform is an effective method for line detection in a digital image. However, the conventional Hough transform can not be applied well enough for an image corrupted by heavy noise. This paper describes a combinatorial fuzzy Hough transform, which enables a detection of not only a blurred line, but also a segment of a line in a very noisy image. It is then extended in order that it can further detect a blurred circle. The effectiveness of the present method has been confirmed by applying it to an actual microphotograph for cytodiagnosis. It can detect the nuclei in a cell cluster in a very noisy medical image.
