Recognition of unconstrained handwritten numerals using biorthogonal spline wavelets
Suzete Correia, J.M. de Carvalho · 2002
The work proposes a novel approach for recognition of unconstrained handwritten numerals using the biorthogonal spline wavelets Cohen-Daubechies-Feauveau (CDF) 3/7 as a feature extractor and a multilayer cluster neural network as a classifier. Experiments with the CENPARMI database show that this method yields good results.