Segmentation of Laser Range Radar Images using Hidden Markov Field Models

Segmentation of images in the context of model based stochastic techniques is connected with high, very often unpracticle computational complexity. The objective with this thesis is to take the models used in model based image processing, simplify and use them in suboptimal, but not computationally demanding algorithms. Algorithms that are essentially one-dimensional, and their extensions to two dimensions are given.The model used in this thesis is the well known hidden Markov model. Estimation of the number of hidden states from observed data, is a problem that is addressed. The state order estimation problem is of general interest and is not specifically connected to image processing. An investigation of three state order estimation techniques for hidden Markov models is given.