A probabilistic algorithm for spatial color image segmentation

Finite mixture models are one of the most widely and commonly used probabilistic techniques for image segmentation. Although the most well known and commonly used distribution when considering mixture models is the Gaussian, it is certainly not the best approximation for image segmentation and other related image processing problems. In this paper, we propose to use finite Dirichlet mixture model (DMM), which offers more flexibility in data modeling, for image segmentation. A maximum likelihood (ML) based algorithm is applied for estimating the resulted segmentation model´s parameters. Spatial information is also employed for figuring out the number of regions in an image and two color spaces are investigated and compared. The experimental results show that the proposed segmentation framework yields good overall performance that is better than a comparable technique based on Gaussian mixture model.