Multi-resolution shape description by corners

TitleMulti-resolution shape description by corners
Publication TypeConference Papers
Year of Publication1992
AuthorsFermüller C, Kropatsch W
Conference Name, 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92
Date Published1992/06/15/18
ISBN Number0-8186-2855-3
Keywordsambiguities, Automation, computational geometry, Computer vision, continuous curves, corners, curvature extrema, curvature information, curve fitting, digital images, Feature extraction, IMAGE PROCESSING, image resolution, Image segmentation, Laboratories, multiple resolution, multiresolution structure, parallelizable, planar curves, Robustness, Sampling methods, scale-space, SHAPE, Smoothing methods, varying scale

A robust method for describing planar curves in multiple resolution using curvature information is presented. The method is developed by taking into account the discrete nature of digital images as well as the discrete aspect of a multiresolution structure (pyramid). The main contribution lies in the robustness of the technique, which is due to the additional information that is extracted from observing the behavior of corners in the whole pyramid. Furthermore, the resulting algorithm is conceptually simple and easily parallelizable. Theoretical results are developed analyzing the curvature of continuous curves in scale-space and showing the behavior of curvature extrema under varying scale. The results are used to eliminate any ambiguities that might arise from sampling problems due to the discreteness of the representation. Experimental results demonstrate the potential of the method