Multiple classifier fusion in probabilistic neural networks

0410828 - UTIA-B 20020042 RIV GB eng J - Článek v odborném periodiku
Grim, Jiří - Kittler, J. - Pudil, Pavel - Somol, Petr
Multiple classifier fusion in probabilistic neural networks.
Pattern Analysis and Applications. Roč. 5, č. 7 (2002), s. 221-233. ISSN 1433-7541. E-ISSN 1433-755X
Grant CEP: GA ČR GA402/01/0981
Výzkumný záměr: CEZ:AV0Z1075907
Klíčová slova: EM algorithm * information preserving transform * multiple classifier fusion
Kód oboru RIV: BB - Aplikovaná statistika, operační výzkum
Impakt faktor: 0.667, rok: 2002

The main motivation of the present paper is to design a statistically well justified and biologically compatible neural network model and to suggest a theoretical interpretation of the high parallelism of biological neural networks. We consider a probabilistic approach to neural networks in the framework of statistical pattern recognition. The complete method based on EM algorithm has been applied to recognize unconstrained handwritten numerals from the database of the Concordia University Montreal.
Trvalý link: http://hdl.handle.net/11104/0130915