A serial combination of connectionist-based classifiers for OCR |
| |
Authors: | E Francesconi M Gori S Marinai G Soda |
| |
Affiliation: | (1) DSI, Università di Firenze, Via S. Marta 3, 50139 Firenze, Italy; e-mail: {enrico,simone,giovanni}@dsi.unifi.it , IT;(2) DII, Università di Siena, Via Roma 56, 53100 Siena, Italy; e-mail: marco@ing.unisi.it , IT |
| |
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.
Received March 6, 2000 / Revised July 12, 2000 |
| |
Keywords: | : Autoassociators – Multilayer Perceptrons – Neural Networks – OCR – Serial Combination of Classifiers |
本文献已被 SpringerLink 等数据库收录! |
|