The problem of interactive foreground/background segmentation in still images is of great practical importance in image editing. The state of the art in interactive segmentation is probably represented by the graph cut algorithm of Boykov and Jolly (ICCV 2001). Its underlying model using both colour and contrast information, together with a strong prior for region coherence. Estimation is performed by solving a graph cut problem for which very efficient algorithms have recently been developed. However the model depends on parameters which must be set by hand and the aim of this work is for those constants to be learned from image data. First, a generative, probabilistic formulation of the model is set out in terms of a `Gaussian Mixture Markov Random Field' (GMMRF). Secondly, a pseudolikelihood algorithm is derived which jointly learns the colour mixture and coherence parameters for foreground and background respectively. Erro rates for GMMRF segmentation are calculated throughout using a new image database, available on the web, with ground truth provided by a human segmenter. The graph cut algorithm, using the learned parameters, generates good object-segmentations with little interaction. However, pseudolikelihood learning proves to be frail, which limits the complexity of usable models, and hence also the achievable error rate.
A user specified trimap splits the image into 3 distinct regions. In the foreground and background regions, we train a Gaussian Mixture Markov Random Field (GMMRF) model, and use this to infer the foreground and background colours, and alpha value in the intermediate region.