Alternate Title
New Applications and Enhancements in the Theory of the GDB-ICP Registration Algorithm
Abstract
Lowe Keypoints and SIFT descriptor: Lowe Keypoints, Laplacian-of-Gaussian Operator, Local maximum in both spatial and scale dimensions, SIFT descriptor, Invariant to similarity transformation by normalizing the image patch using the scale and the dominant orientation.Histogram of local gradient within the patch, normalized to be invariant to affine intensity transformation.
Keywords
GDB-ICP, SIFT
Subject Categories
Imaging systems
Disciplines
Engineering
Publisher
Bernard M. Gordon Center for Subsurface Sensing and Imaging Systems (Gordon-CenSSIS)
Publication Date
2007
Rights Holder
Bernard M. Gordon Center for Subsurface Sensing and Imaging Systems (Gordon-CenSSIS)
Permanent URL
Recommended Citation
Yang, Gehua; Sofka, Michal; Kelman, Avital; and Stewart, Charles V., "Improvements on GDB-ICP Registration Algorithm with Applications to Natural-Scene, Retina, and Brain Images" (2007). Research Thrust R2 Presentations. Paper 22. http://hdl.handle.net/2047/d10009024
Click button above to open, or right-click to save.
Notes
Poster presented at the 2007 Thrust R2D Image Understanding and Sensor Fusion Methods Conference