MIR: An Approach to Robust Clustering--Application to Range Image Segmentation

This paper describes an unsupervised region merging technique based on a novel robust statistical test. The merging decision is derived from the mutual inlier ratio (MIR) of adjacent regions. This ratio is computed using robust regression techniques and a novel method to estimate the robust scale of the Gaussian distribution. A discrimination value to recognize identical Gaussian distributions with the MIR is derived theoretically as a function of the sizes of the compared sets. The presented method to test distributions is compared with the established Kolmogorov-Smirnov test and implemented into a segmentation algorithm for planar range images. The iterative region growing technique is evaluated using an established framework for range image segmentation comparison involving 60 real range images. The evaluation incorporates a comparison with four state-of-the-art algorithms and gives an experimental demonstration of the need for robust methods capable of handling noisy data in real applications. Index Terms--Segmentation, robust statistics, region merging, range images, clustering, least-median-of-squares, segmentation comparison.