CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2007 vol.29 Issue No.03 - March
Issue No.03 - March (2007 vol.29)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2007.50
The Curvature Scale Space (CSS) technique is considered to be a modern tool in image processing and computer vision. Direct Curvature Scale Space (DCSS) is defined as the CSS that results from convolving the curvature of a planar curve with a Gaussian kernel directly. In this paper we present a theoretical analysis of DCSS in detecting corners on planar curves. The scale space behavior of isolated single and double corner models is investigated and a number of model properties are specified which enable us to transform a DCSS image into a tree organization and, so that corners can be detected in a multiscale sense. To overcome the sensitivity of DCSS to noise, a hybrid strategy to apply CSS and DCSS is suggested.
Scale space, curve convolution, Gaussian smoothing, curvature, corner detection.
Baojiang Zhong, Wenhe Liao, "Direct Curvature Scale Space: Theory and Corner Detection", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.29, no. 3, pp. 508-512, March 2007, doi:10.1109/TPAMI.2007.50