Landmark-Based Image Analysis: Using Geometric and Intensity Models
Landmarks are preferred image features for a variety of computer vision tasks such as image mensuration, registration, camera calibration, motion analysis, 3D scene reconstruction, and object recognition. Main advantages of using landmarks are robustness w. r. t. lightning conditions and other radiometric vari ations as well as the ability to cope with large displacements in registration or motion analysis tasks. Also, landmark-based approaches are in general com putationally efficient, particularly when using point landmarks. Note, that the term landmark comprises both artificial and natural landmarks. Examples are comers or other characteristic points in video images, ground control points in aerial images, anatomical landmarks in medical images, prominent facial points used for biometric verification, markers at human joints used for motion capture in virtual reality applications, or in- and outdoor landmarks used for autonomous navigation of robots. This book covers the extraction oflandmarks from images as well as the use of these features for elastic image registration. Our emphasis is onmodel-based approaches, i. e. on the use of explicitly represented knowledge in image analy sis. We principally distinguish between geometric models describing the shape of objects (typically their contours) and intensity models, which directly repre sent the image intensities, i. e. ,the appearance of objects. Based on these classes of models we develop algorithms and methods for analyzing multimodality im ages such as traditional 20 video images or 3D medical tomographic images.
What people are saying - Write a review
We haven't found any reviews in the usual places.
2D and 3D 3D differential operators 3D images 3D MR image 3D operators affine transformation algorithms analytic anatomical point landmarks applied approximating thin-plate splines basis functions blur characterization comparison computer graphics computer vision consider contour corner operators corresponding Cramer-Rao bound CT images curve dataset deformations denoted described detection performance differential operators elastic registration error ellipsoid estimated example false detections Figure Forstner Gaussian curvature geometric models gradient Hessian matrix human brain image analysis image data image features image gradient image intensities image noise image registration intensity models intensity variations interpolating thin-plate splines isocontour L-corner landmark extraction landmarks in 3D localization errors mathematical matrix mean curvature measure medical image model-based normal landmarks Note objects obtain operator Op3 operator responses order partial derivatives orientation parameters partial derivatives position principal curvatures problem Proc quasi-landmarks registration result represent Rohr saddle points scheme Section slices solution step edge surface vector ventricular horn ventricular system voxels
Page 282 - Maciunas, RJ, and Fitzpatrick, JM, "Registration of head CT images to physical space using a weighted combination of points and surfaces," IEEE Transactions on Medical Imaging, 17, pp.
Page 296 - New feature points based on geometric invariants for 3D image registration," International Journal of Computer Vision 18, pp.
Page 283 - JV Miller, DE Breen, WE Lorensen, RM O'Bara, and MJ Wozny. Geometrically Deformed Models: A method for extracting closed geometric models from volume data.
Page 283 - On the problem of geometric distortion in Magnetic Resonance Images for Stereotactic Neurosurgery,