Title :
Metaclasses and zoning for handwritten document recognition
Author :
Macario, V. ; Silva, G.F.P. ; Souza, M.R.P. ; Zanchettin, Cleber ; Cavalcanti, G.D.C.
Author_Institution :
Dept. of Estatistics & Inf., Rural Fed. of Pernambuco, Recife, Brazil
Abstract :
This work presents a complete method for improving the handwritten document recognition. In this task some characters are confused with others because of their visual/structural similarity. A SOM and TreeSOM neural network were used to sort different characters in metaclasses. In each metaclass a zoning approach was applied trying to get particular features to improve the character classification. The experiments with this new approach were performed in the NIST database with the classic MLP and a fast neural network RBF-DDA.
Keywords :
document image processing; handwriting recognition; image classification; radial basis function networks; self-organising feature maps; trees (mathematics); NIST database; TreeSOM neural network; character classification; classic MLP; handwritten document recognition; metaclasses; neural network RBF-DDA; structural similarity; visual similarity; zoning; Character recognition; Feature extraction; Handwriting recognition; Neural networks; Shape; Training;
Conference_Titel :
Neural Networks (IJCNN), The 2013 International Joint Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4673-6128-6
DOI :
10.1109/IJCNN.2013.6707056
