%0 Conference Proceedings
%A Júnior, Iális Cavalcante de Paula,
%A Medeiros, Fátima Nelsizeuma Sombra de,
%A Bezerra, Francisco Nivando,
%A Ushizima, Daniela Mayumi,
%@affiliation Universidade Federal do Ceará
%@affiliation Universidade Federal do Ceará
%@affiliation Instituto Federal de Educação, Ciência e Tecnologia
%@affiliation Lawrence Berkeley National Laboratory
%T Corner detection within a multiscale framework
%B Conference on Graphics, Patterns and Images, 24 (SIBGRAPI)
%D 2011
%E Lewiner, Thomas,
%E Torres, Ricardo,
%S Proceedings
%8 Aug. 28 - 31, 2011
%J Los Alamitos
%I IEEE Computer Society
%C Maceió
%K corner detection, high curvature points (HCP), shape reconstruction, curvature space-scale (CSS).
%X We present a new multiscale method for corner detection. The proposed algorithm embodies an undecimated wavelet decomposition of the angulation signal of a shape contour to identify significant points on it. It detects peaks that persist through several scales from the correlation signal between scales of its non-orthogonal sub-band decompositions. These peaks correspond to high curvature points (HCPs). Furthermore, we compare the proposed method with others available in the literature, including the well-known curvature scale-space (CSS) method. The quantitative assessment of the algorithms is provided by some figures of merit (FOM) measures that indicate which method better detects the relevant points in terms of compaction and shape reconstruction.
%@language en
%3 Camera_Ready_SIBGRAPI.pdf