Multiple Landmark Warping Using Thin-plate Splines
نویسندگان
چکیده
Image warping plays an extremely important role in face matching and recognition and therefore has wide applications and great significance in computer vision, biomedical imaging and homeland security. One popular warping algorithm developed by Alex Rosen, known as AlexWarp has the drawback that it only allows one pair of landmarks being specified at one time. The consequence of this is that the destination landmarks are displaced in the subsequent warping. We develop an image warping algorithm using thin-plate splines that allows multilandmarks being specified and warped simultaneously. The space transformation is the solution of minimizing a thin-plate deformation energy. QR decomposition techniques are used to stabilize the solution. We apply the new warping algorithm to various face matching situations. † Department of Computing and Mathematical Sciences, Texas A&M University Corpus Christi, Presenter Telephone (361) 334-0589 Fax (361) 887-9009 Email [email protected] ‡ Department of Computing and Mathematical Sciences, Texas A&M University Corpus Christi Telephone (361) 825-3492 Fax (361) 825-2795 Email [email protected] We acknowledge support from Texas Research Development Fund 140100-34025 and Texas Engineering and Technical Consortium Grant 011161-CS2003
منابع مشابه
Warping a Neuro-Anatomy Atlas on 3D MRI Data with Radial Basis Functions
Navigation for neurosurgical procedures must be highly accurate. Often small structures are hardly seen on pre-operative scans. Fitting a 3D electronic neuroanatomical atlas on the data assists with the localization of small structures and dim outlines. During surgery also brainshifts occurs. With intra-operative MRI the preoperative MRI can be warped to the real 3D situation. The paper describ...
متن کاملA Comparison of Thin Plate and Spherical Splines with Multiple Regression
Thin plate and spherical splines are nonparametric methods suitable for spatial data analysis. Thin plate splines acquire efficient practical and high precision solutions in spatial interpolations. Two components in the model fitting is considered: spatial deviations of data and the model roughness. On the other hand, in parametric regression, the relationship between explanatory and response v...
متن کاملAutomation of Landmark Selection for Rodent Brainmri-histology Registration Using Thin-plate Splines
متن کامل
Approximating Thin-Plate Splines for Elasti Registration: Integration of Landmark Errors and Orientation Attributes
متن کامل
Image Registration Based on Thin-Plate Splines and Local Estimates of Anisotropic Landmark Localization Uncertainties
We present an approach to elastic registration of tomographic brain images which is based on thin plate splines and takes into account landmark errors The inclusion of error information is important in clin ical applications since landmark extraction is always prone to error In comparison to previous work our approach can cope with anisotropic er rors which is signi cantly more realistic than d...
متن کامل