Select and split fuzzy cell Hough transform-a fast and efficient method to detect contours in images

In this paper a new variation of Hough transform is proposed. The parameter space of Hough Transform is iteratively split into fuzzy cells which are defined as fuzzy numbers. Each fuzzy cell corresponds to a fuzzy curve in the spatial domain. After each iteration the fuzziness of the cells is reduced and the curves are estimated with better accuracy. The uncertainty of the contour point location is transferred to the parameter space and gives better accuracy in curve estimation than the classical Hough transform, especially when noisy images have to be used. Moreover, the computation time is significantly decreased, since the regions of the parameter space where contours do not correspond, are rejected during the iterations.