Efficient technique for ellipse detection using restricted randomized Hough transform

We propose a new efficient method to detect ellipses in binary or gray-scale images, called restricted randomized Hough transform (RRHT). The key of RRHT is to restrict the scope of selected points when detecting ellipses by prior image processing, from which the information of curves can be obtained and further work focuses on detection and validation of each curve orderly. Artificial images and natural gray images are employed to test this method and the results show that RRHT spends less time to detect ellipses more successfully compared with that of conventional randomized Hough transform (RHT).