40 search results - page 2 / 8 » A trainable feature extractor for handwritten digit recognit... |
ESANN
2006
13 years 10 months ago
2006
We investigate when sparse coding of sensory inputs can improve performance in a classification task. For this purpose, we use a standard data set, the MNIST database of handwritte...
ICPR
2002
IEEE
14 years 10 months ago
2002
IEEE
This paper discusses the use of genetic algorithm for feature selection for handwriting recognition. Its novelty lies in the use of a multi-objective genetic algorithms where sens...
INFORMATICASI
2008
13 years 9 months ago
2008
MVA
2010
13 years 4 months ago
2010
CIARP
2009
Springer
14 years 3 months ago
2009
Springer
This paper brings a contribution to the problem of efficiently recognizing handwritten words from a limited size lexicon. For that, a multiple classifier system has been developed...