Efficient image understanding based on the Markov random field model and error backpropagation network

Image labeling is a process of recognizing each segmented region, properly exploiting the properties of the regions and the spatial relationships between regions. In some sense, image labeling is an optimization process of indexing regions using the constraints as to the scene knowledge. This paper further investigates a method of efficiently labeling images using the Markov random field (MRF). MRF model is defined on the region adjacency graph and the labeling is then optimally determined using simulated annealing. The MRF model parameters are automatically estimated using the error backpropagation network. The authors analyze the proposed method through experiments using the real natural scene images.<>