Image Feature Selection Using Modified ICM Method

This paper discusses a version of the ICM method in which the contextual information is modeled by Markov random fields (MRF). To select the feature, a new local MRF model with a fitting block neighborhood is introduced. This model extracts contextual information not only from the relative intensity levels but also from the geometrically directional position of neighboring cliques. Feature selection depends on each block's contribution to the local variance. They discriminates it into binary regions, context and background. Boundary between two regions is also distinctive. The proposed algorithm performs segmentation using directional block fitting procedure which confines merging to spatially adjacent elements and generates a partition such that pixels in unified cluster have a homogeneous intensity level. From experiment with ink rubbed copy images, this method is determined to be quite effective for feature identification. In particular, the new algorithm preserves the details of the images well, without over- and under-smoothing problem occurring in general iterated conditional modes (ICM). It should be noted that the smoothing effect is not serious in this approach.