Transformation of optimized prototypes for handwritten digit recognition
Hong Yan · 2002
Proposes a method for handwritten digit recognition using optimized prototypes generated through learning and transformation. In this method a set of prototypes are obtained from training samples and mapped to a multi-layer neural network for optimization to improve their classification power. The new prototypes are then transformed geometrically to produce a larger set of prototypes for recognition of testing samples. The method has been verified to work well in experimental studies.>