학술논문
2D Shape Recognition Using Information Theoretic Kernels
Document Type
Conference
Author
Source
2010 20th International Conference on Pattern Recognition Pattern Recognition (ICPR), 2010 20th International Conference on. :25-28 Aug, 2010
Subject
Language
ISSN
1051-4651
Abstract
In this paper, a novel approach for contour based 2D shape recognition is proposed, using a class of information theoretic kernels recently introduced. This kind of kernels, based on a non-extensive generalization of the classical Shannon information theory, are defined on probability measures. In the proposed approach, chain code representations are first extracted from the contours; then n-gram statistics are computed and used as input to the information theoretic kernels. We tested different versions of such kernels, using support vector machine and nearest neighbor classifiers. An experimental evaluation on the Chicken pieces dataset shows that the proposed approach significantly outperforms the current state-of-the-art methods.