Fuzzy C-Means Inspired Free Form Deformation Technique for Registration

This paper presents a novel method aimed to free form deformation function approximation for purpose of image registration. The method is currently feature-based. The algorithm is inspired to concepts derived from Fuzzy C-means clustering technique such as membership degree and cluster centroids. After algorithm explanation, tests and relative results obtained are presented and discussed. Finally, considerations on future improvements are elucidated.

[1]  Richard A. Robb,et al.  Visualization in biomedical computing , 1999, Parallel Comput..

[2]  Adrien Bartoli,et al.  Generalized Thin-Plate SplineWarps , 2007, CVPR.

[3]  Alan C. Evans,et al.  An Extensible MRI Simulator for Post-Processing Evaluation , 1996, VBC.

[4]  D. Louis Collins,et al.  Design and construction of a realistic digital brain phantom , 1998, IEEE Transactions on Medical Imaging.

[5]  Gary E. Christensen,et al.  Consistent landmark and intensity-based image registration , 2002, IEEE Transactions on Medical Imaging.

[6]  Alan C. Evans,et al.  MRI Simulation Based Evaluation and Classifications Methods , 1999, IEEE Trans. Medical Imaging.

[7]  Karl Rohr,et al.  Incorporation of Landmark Error Ellipsoids for Image Registration Based on Approximating Thin-Plate Splines , 1998 .

[8]  Nira Dyn,et al.  Image Warping by Radial Basis Functions: Application to Facial Expressions , 1994, CVGIP Graph. Model. Image Process..

[9]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[10]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[11]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Adrien Bartoli,et al.  Generalized Thin-Plate Spline Warps , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.