A Moving Least Square Based Framework for Thoracic CT Image Registration

Abstract

This chapter proposes an automatic registration process for tracing of the deformity path of the thoracic region based on feature detector cum descriptor Speeded Up Robust Feature (SURF) and Moving Least Squares (MLS). Corresponding control point pairs or landmarks in image pairs or groups can be used to define the deformation with respect to time, point of view, or modality. The manual definition of the number of control points in an image such that it is enough to define all kinds of deformations in that respective image is a tedious task. Hence, an automatic definition of control points has been the way forward taken in the proposed work. The control point cloud on the images is defined by its feature set which is obtained by using the SURF detector/descriptor, which serves as an input for MLS algorithm to trace the deformations of the image (thoracic image in this case).