Abstract.
In this paper we describe the connectionist-based classification engine of an OCR system. The classification engine is based on a new modular connectionist architecture, where a multilayer perceptron (MLP) acting as a classifier is properly combined with a set of autoassociators – one for each class – trained to copy the input to the output layer. The MLP-based classifier selects a small group of classes with high score, that are afterwards verified by the corresponding autoassociators. The learning samples used to train the classifiers are constructed by means of a synthetic noise generator starting from few grey level characters labeled by the user. We report experimental results for comparing three neural architectures: an MLP-based classifier, an autoassociator-based classifier, and the proposed combined architecture. The experiments show that the proposed architecture exhibits the best performance, without increasing significantly the computational burden.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received March 6, 2000 / Revised July 12, 2000
Rights and permissions
About this article
Cite this article
Francesconi, E., Gori, M., Marinai, S. et al. A serial combination of connectionist-based classifiers for OCR. IJDAR 3, 160–168 (2001). https://doi.org/10.1007/PL00013556
Issue Date:
DOI: https://doi.org/10.1007/PL00013556