A Novel Approach for Image Alignment Using a Markov-Gibbs Appearance Model

A new approach to align an image of a medical object with a given prototype is proposed. Visual appearance of the images, after equalizing their signals, is modelled with a new Markov-Gibbs random field with pairwise interaction model. Similarity to the prototype is measured by a Gibbs energy of signal co-occurrences in a characteristic subset of pixel pairs derived automatically from the prototype. An object is aligned by an affine transformation maximizing the similarity by using an automatic initialization followed by gradient search. Experiments confirm that our approach aligns complex objects better than popular conventional algorithms.

[1]  Max A. Viergever,et al.  A survey of medical image registration , 1998, Medical Image Anal..

[2]  James Theiler,et al.  Automated image registration (AIR) of MTI imagery , 2003, SPIE Defense + Commercial Sensing.

[3]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[4]  Max A. Viergever,et al.  Mutual-information-based registration of medical images: a survey , 2003, IEEE Transactions on Medical Imaging.

[5]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[6]  Aly A. Farag,et al.  Precise segmentation of multimodal images , 2006, IEEE Transactions on Image Processing.

[7]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.