The work presented in this thesis proposes several methods that can be roughly divided into three different categories: I) landmark localization in medical images, II) feature matching for image registration, and III) biomarker discovery in neuroimaging. The first part deals with the identification of anatomical landmarks. The motivation stems from the fact that the manual identification and la...

Motivation A new interest region operator and feature descriptor called Center-Surround Distribution Distance (CSDD) is based on comparing feature distributions between a central foreground region and a surrounding ring of background pixels. In addition to finding light(dark) blobs surrounded by a dark(light) background, CSDD also detects blobs with arbitrary color distribution that “stand out”...

A novel method for robust estimation, called Graph-Cut RANSAC1, GC-RANSAC in short, is introduced. To separate inliers and outliers, it runs the graph-cut algorithm in the local optimization (LO) step which is applied when a sofar-the-best model is found. The proposed LO step is conceptually simple, easy to implement, globally optimal and efficient. GC-RANSAC is shown experimentally, both on sy...

A binocular point matching method using affine transformation is presented in this paper to deal with matching ambiguities. The epipolar geometry is used to determine all the possible matching pairs to form an initial correspondence data set. Then, an affine registration model with four parameters that is invariant to scaling, rotation and translation is built using the Random Sample Consensus ...

This article presents a new approach to matching occupancy grid maps by means of finding correspondences between a set of sparse features detected in the maps. The problem is stated here as a special instance of generic image registration. To cope with the uncertainty and ambiguity that arise from matching grid maps, we introduce a modified RANSAC algorithm which searches for a dynamic number o...

Terrestrial laser scanners have become a standard piece of surveying equipment, used in diverse fields like geomatics, manufacturing and medicine. However, the processing of today’s large point clouds is time-consuming, cumbersome and not automated enough. A basic step of post-processing is the registration of scans from different viewpoints. At present this is still done using artificial targe...

Terrestrial laser scanning (TLS) is an efficient tool to capture the point cloud for facade modeling. However, it not easy obtain position by Global Navigation Satellite System (GNSS) as occluded high buildings, which would lead a problem orienting TLS data target coordinate system. In this paper, we propose coarse-to-fine registration method reliably orient using digital line graph (DLG). The ...

In the present day, 3D point clouds are considered to be an important form of representing world. computer vision, mobile robotics, and graphics, cloud registration is a basic task, it widely used in reconstruction, reverse engineering, among other applications. However, mainstream method subject problems long time as well poor modeling effect, these two factors cannot balanced. To address this...