Abstract: A novel range image segmentation algorithm based on RHT (Randomized Hough Transform) is presented in the paper. The algorithm finds planar regions by utilizing RHT and has the advantage of insensitivity to noise. The proposed algorithm has been tested on a popular range image database (ABW image database) with comparisons to four typical range image segmentation algorithms. The experiment results show that the proposed algorithm has a strong anti-noise ability and its segmentation performance is superior to the four algorithms tested.