Multi-Step Procedures for the Localization of 2D and 3D Point Landmarks and Automatic ROI Size Selection

In this contribution, we are concerned with the detection and refined localization of 3D point landmarks. We propose multi-step differential procedures for subvoxel localization of 3D point landmarks. Moreover, we address the problem of choosing an optimal size for a region-of-interest (ROI) around point landmarks. That is, to reliably localize the landmark position, on the one hand, as much as possible image information about the landmark should be incorporated. On the other hand, the ROI should be restricted such that other structures do not interfere.

[1]  Karl Rohr.  On 3D differential operators for detecting point landmarks , 1997, Image Vis. Comput..

[2]  K. Rohr,et al.  Investigation of Approaches for the Localization of Anatomical Landmarks in 3D Medical Images , 1997 .

[3]  Paul Beaudet,et al.  Rotationally invariant image operators , 1978 .

[4]  Azriel Rosenfeld,et al.  Gray-level corner detection , 1982, Pattern Recognit. Lett..

[5]  Tony Lindeberg,et al.  Junction detection with automatic selection of detection scales and localization scales , 1994, Proceedings of 1st International Conference on Image Processing.

[6]  Leonie Dreschler,et al.  Ermittlung markanter Punkte auf den Bildern bewegter Objekte und Berechnung einer 3D-Beschreibung auf dieser Grundlage , 1981 .

[7]  Takeo Kanade,et al.  A locally adaptive window for signal matching , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[8]  Karl Rohr,et al.  Modelling and identification of characteristic intensity variations , 1992, Image Vis. Comput..

[9]  J. Alison Noble,et al.  Finding Corners , 1988, Alvey Vision Conference.

[10]  Jean-Philippe Thirion,et al.  Extremal points: definition and application to 3D image registration , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.