The Community for Technology Leaders
Green Image
<p><b>Abstract</b>—We incorporate prior knowledge to construct nonlinear algorithms for invariant feature extraction and discrimination. Employing a unified framework in terms of a nonlinearized variant of the Rayleigh coefficient, we propose nonlinear generalizations of Fisher's discriminant and oriented PCA using support vector kernel functions. Extensive simulations show the utility of our approach.</p>
Fisher's discriminant, nonlinear feature extraction, support vector machine, kernel functions, Rayleigh coefficient, oriented PCA.

J. Weston, A. Smola, S. Mika, K. Müller, B. Schölkopf and G. Rätsch, "Constructing Descriptive and Discriminative Nonlinear Features: Rayleigh Coefficients in Kernel Feature Spaces," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 25, no. , pp. 623-633, 2003.
94 ms
(Ver 3.3 (11022016))