A Gaussian-mixture-based image segmentation algorithm

This paper focuses on the formulation, development, and evaluation of an autonomous segmentation algorithm which can segment targets in a wide class of highly degraded images. A segmentation algorithm based on a Gaussian-mixture model of a two-class image is selected because it has the potential for effective segmentation provided that the histogram of the image approximates a Gaussian mixture and the parameters of the model can be estimated accurately. A selective sampling approach based on the Laplacian of the image is developed to transform the histogram of any image into an approximation of a Gaussian mixture and a new estimation method which uses information derived from the tails of the mixture density is formulated to estimate the model parameters. The resulting selective-sampling-Gaussian-mixture parameter-estimation segmentation algorithm is tested and evaluated on a set of real degraded target images and the results show that the algorithm is able to accurately segment diverse images. (C) 1997 Pattern Recognition Society. Published by Elsevier Science Ltd.