Title: Shape matching through contour extraction using Circular Augmented Rotational Trajectory (CART) algorithm
Authors: Russel A. Apu, Marina L. Gavrilova
Addresses: Department of Computer Science, University of Calgary, 2500 University Drive NW, Calgary, AB T2N 1N4, Canada. ' Department of Computer Science, University of Calgary, 2500 University Drive NW, Calgary, AB T2N 1N4, Canada
Abstract: A novel Circular Augmented Rotational Trajectory (CART) algorithm to compute an R-Space based shape descriptors, allowing efficient shape matching, generalisation and classification, is given. The shape descriptor is rotation and scale invariant, capable of detecting invariant geometric properties despite the presence of considerable noise and quantisation errors. The method is capable of detecting distinctive features including general invariant curvatures and sharp features while properly addressing the ambiguity in shape approximation. Experimental analysis on complex and ambiguous shapes shows that the CART method can correctly detect and represent the inherent shape. Universality, robustness and consistent performance have been noted while applying to many difficult and ambiguous object boundaries.
Keywords: R-Space; shape recognition; intelligent data processing; CART; circular augmented rotational trajectory; shape matching; shape classification; feature detection; invariant curvatures; sharp features; shape approximation; object boundaries.
International Journal of Business Intelligence and Data Mining, 2010 Vol.5 No.2, pp.192 - 210
Available online: 27 Jan 2010 *Full-text access for editors Access for subscribers Purchase this article Comment on this article