Detection of planar facets in noisy range images

Segmentation of the image is one of the major tasks of a machine vision system designed for constructing a three-dimensional representation of the object being imaged. A robust approach for segmenting planar surfaces from range images is presented in this paper. An algorithm based on clustering through fuzzy covariance matrices, which has been proposed by Gustafson and Kessel is considered for planar segmentation. However this algorithm performs poorly if the data is noisy, which is usually the case in real life applications. In order to handle noisy data, a robust modification, based on the noise clustering concept, is introduced to the algorithm. This modification is found to work very well in noisy data. Another alogrithm called the Adaptive Fuzzy c-Elliptotypes has been used by Dave for detecting lines in 2-D digital images, this algorithm is also considered for range image segmentation. The robust modification of this algorithm is used for planar segmentation of 3-D range images and is found to perform well. Examples of range image data are included to show the effectiveness of the algorithms proposed