We have developed a new mutual information-based registration method for matching unlabeled point features. In contrast to earlier mutual information-based registration methods which estimate the mutual information using image intensity information, our approach uses the point feature location information. A novel aspect of our approach is the emergence of correspondence (between the two sets of features) as a natural by-product of joint density estimation. We have applied this algorithm to the problem of geometric alignment of primate autoradiographs. We also present preliminary results on 3D robust matching of sulci derived from anatomical MR. Finally, we present an experimental comparison between the mutual information approach and other recent approaches which explicitly parameterize feature correspondence. Keywords: point feature registration, rigid alignment, mutual information, similarity transformation, spatial mapping, correspondence, joint probability, softassign Received ?...

We propose a segmentation method based on Polya’s urn model for contagious phenomena. A preliminary segmentation yields the initial composition of an urn representing the pixel. The resulting urns are then subjected to a modified urn sampling scheme mimicking the development of an infection to yield a segmentation of the image into homogeneous regions. This process is implemented using contagion urn processes and generalizes Polya’s scheme by allowing spatial interactions. The composition of the urns is iteratively updated by assuming a spatial Markovian relationship between neighboring pixel labels. The asymptotic behavior of this process is examined and comparisons with simulated annealing and relaxation labeling are presented. Examples of the application of this scheme to the segmentation of synthetic texture images, ultra-wideband synthetic aperture radar (UWB SAR) images and magnetic resonance images (MRI) are provided.

Abstract—In the problems of localization using inaccurate maps, navigation agents have to match available information from sensors to maps in order to find their locations. A map contains a set of constraints that can be expressed in the form of a graphical model that matching algorithm has to satisfy. There are two generally categories of constraints: absolute and relative. We propose a relaxation-based algorithm for the NPhard problem of one-to-one feature matching with absolute and relative constraints. The algorithm is a combination between relaxation labeling and the Kuhn-Munkres method where the former is known for its highly parallel structure imitated the human visual process. To test the performance, we applied the algorithm in a robotics application where the objective is to match range scanner features to those in inaccurate template maps provided by humans. Our experiments show that the proposed algorithm can achieve qualified matching results in artificial and real situations. I.