Arthur Goshtasby (Advisor), Jack Jean (Committee Member), Thomas Wischgoll (Committee Member)
Master of Science in Computer Engineering (MSCE)
A triangulation-based approach to nonrigid image registration is presented. This method builds upon control point projective registration methods. Control points for this method are located using the Harris point detector. An analysis is presented for this detector to show its properties. Projective registration is used as the basis for this non-rigid registration method. Details of the projective registration method used are presented. Nonrigid registration is used to spatially align images of a 3-D scene taken from different views. Projective registration approximates the scene geometry as a plane. This nonrigid approach subdivides the images into small corresponding triangles, to improve the approximation of the scene geometry. Affine transformation functions are used to register corresponding triangles. Finally a refinement step is presented to smooth the transition between adjacent triangles and achieve a smooth registration across the image domain.
Department or Program
Department of Computer Science and Engineering
Year Degree Awarded
Copyright 2011, all rights reserved. This open access ETD is published by Wright State University and OhioLINK.