Year: 2008
Type: article
Abstract: The detection of stable feature points is an important preprocessing step for many applications in computer graphics. Especially,\nregistration and matching often require feature points and depend heavily on their quality. In the 2D image case, scale\nspace based feature detection is well established and shows unquestionably good results. We introduce a novel scale space\ngeneralization to 3D embedded surfaces for extracting surface features. In contrast to a straightforward generalization to 3D\nimages our approach extracts intrinsic features. We argue that such features are superior, in particular in the context of partial\nmatching. Our features are robust to noise and provide a good description of the object’s salient regions.
Authors: Markus Schlattmann, Patrick Degener, Reinhard Klein
Language: English
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2400454826