Rigid registration of 3-D objects by motion analysis

The registration of 3-D objects is an important problem in the image processing field. When using landmarks or specific features is not possible for that task, iterative methods can be used with profit, but suffer from the presence of local minima. We present here a general iterative method for the registration of 3-D objects. Its originality stems from its mechanical basis: we study the motion of a rigid object in a potential field. This particular approach takes into account the kinetic energy of the object, which allows the avoidance of some local minima. We provide a comparison of our method with other ones and present result from real medical data.

[1]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  P. Danielsson Euclidean distance mapping , 1980 .

[3]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[4]  Grégoire Malandain,et al.  Improving Registration of 3-D Medical Images Using a Mechanical Based Method , 1994, ECCV.

[5]  Gunilla Borgefors,et al.  Distance transformations in digital images , 1986, Comput. Vis. Graph. Image Process..

[6]  Gunilla Borgefors,et al.  Hierarchical Chamfer Matching: A Parametric Edge Matching Algorithm , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  M. Viergever,et al.  Medical image matching-a review with classification , 1993, IEEE Engineering in Medicine and Biology Magazine.