Conference paper

 
Štrba, M., Herout, A., Havel, J.: Handwritten Digits Recognition Improved by Multiresolution Classifier Fusion, In: Proceedings of IbPRIA 2011, LNCS, Berlin, DE, Springer, 2011, p. 726-733, ISBN 978-3-642-21256-7
Publication language:english
Original title:Handwritten Digits Recognition Improved by Multiresolution Classifier Fusion
Title (cs):Rozpoznávání ručně psaných číslic vylepšeno fúzí klasifikátorů v různých rozlišeních
Pages:726-733
Proceedings:Proceedings of IbPRIA 2011, LNCS
Conference:Iberian Conference on Pattern Recognition and Image Analysis
Place:Berlin, DE
Year:2011
ISBN:978-3-642-21256-7
Publisher:Springer Verlag
Keywords
Digit Recognition, Classifier Fusion, Multiresolution
Annotation
One common approach to construction of highly accurate classifiers for hadwritten digit recognition is fusion of several weaker classifiers into a compound one, which (when meeting some constraints) outperforms all the individual fused classifiers.  This paper studies the possibility of fusing classifiers of different kinds (Self-Organizing Maps, Randomized Trees, and AdaBoost with MB-LBP weak hypotheses) constructed on training sets resampled to different resolutions.  While it is common to select one resolution of the input samples as the ``ideal one'' and fuse classifiers constructed for it, this paper shows that the accuracy of classification can be improved by fusing information from several scales.
BibTeX:
@INPROCEEDINGS{
   author = {Miroslav Štrba and Adam Herout and Jiří Havel},
   title = {Handwritten Digits Recognition Improved by Multiresolution
	Classifier Fusion},
   pages = {726--733},
   booktitle = {Proceedings of IbPRIA 2011, LNCS},
   year = {2011},
   location = {Berlin, DE},
   publisher = {Springer Verlag},
   ISBN = {978-3-642-21256-7},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9508}
}