Cooperation of GBP and LVQ networks for optical character recognition
Jérôme Loncelle, Nicolas Derycke, Françoise Fogelman Soulié · 2003
One way to solve the real-world optical character recognition (OCR) problems is described. The strategy chosen was to introduce a neural character recognition box into a classical OCR product. The authors recall the different steps involved in the OCR process. Some of the problems arising in the design of a database for the training of neural networks on OCR and recognition are discussed. They tested several multilayer perceptron architectures, using strong constraints and shared weights, and showed that the cooperation between the generalised backpropagation (GBP) and LVQ algorithms resulted in better performance on real-world databases than classical techniques. The speedup of the total recognition process is considered.>