Summary: Published in Proc. of the 16th Int. Conf. on Pattern Recognition (ICPR), Vol. 2, pp. 864­868, 2002. 864
Tangent Distance Kernels for Support Vector Machines
Bernard Haasdonk
Computer Science Department
Albert-Ludwigs-University Freiburg
79110 Freiburg, Germany
haasdonk@informatik.uni-freiburg.de
Daniel Keysers
Lehrstuhl f¨ur Informatik VI, Computer Science Department
RWTH Aachen ­ University of Technology
52056 Aachen, Germany
keysers@informatik.rwth-aachen.de
Abstract
When dealing with pattern recognition problems one en-
counters different types of a-priori knowledge. It is impor-
tant to incorporate such knowledge into the classification
method at hand. A very common type of a-priori knowl-
edge is transformation invariance of the input data, e.g. ge-
ometric transformations of image-data like shifts, scaling
etc. Distance based classification methods can make use of

Source: Albert-Ludwigs-Universität Freiburg, Institut für Informatik,, Lehrstuhls für Mustererkennung und Bildverarbeitung
Haasdonk, Bernard - Institut für Numerische und Angewandte Mathematik, Universität Münster

Collections: Computer Technologies and Information Sciences; Mathematics