AUTOMATIC PATTERN RECOGNITION BY SIMILARITY REPRESENTATIONS - A NOVEL APPROACH

Elżbieta Pȩkalska, Robert P.W. Duin Abstract : The automatic recognition of objects may benefit from using a similarity representation instead of the traditional approach based on features. It is shown th common use of nearest neighbour classifiers for similarity representations may be improved significantly by other classification rules with respect to recognition accur as well as computational complexity.

[1]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[2]  Belur V. Dasarathy,et al.  Nearest neighbor (NN) norms: NN pattern classification techniques , 1991 .

[3]  Anil K. Jain,et al.  A modified Hausdorff distance for object matching , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[4]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[5]  Robert P. W. Duin,et al.  Relational discriminant analysis , 1999, Pattern Recognit. Lett..

[6]  Shimon Edelman,et al.  Representation and recognition in vision , 1999 .

[7]  Robert P. W. Duin,et al.  Classifiers for dissimilarity-based pattern recognition , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[8]  Robert P. W. Duin,et al.  Classifiers in almost empty spaces , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.