Learning Optimization in a MLP Neural Network Applied to OCR

Authors:
Isis Bonet Cruz;Adolfo Díaz Sardiñas;Rafael Bello Pérez;Yanetsy Sardiñas Oliva
Affiliations:
-;-;-;-
Venue:
MICAI '02 Proceedings of the Second Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
Year:
2002

Citing 3
Cited 1

The image processing handbook

The image processing handbook
The scientist and engineer's guide to digital signal processing

The scientist and engineer's guide to digital signal processing
Computer and Robot Vision

Computer and Robot Vision

Predicting Human Immunodeficiency Virus (HIV) Drug Resistance Using Recurrent Neural Networks

IWINAC '07 Proceedings of the 2nd international work-conference on The Interplay Between Natural and Artificial Computation, Part I: Bio-inspired Modeling of Cognitive Tasks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper focuses on the possibilities of optimization of the training process of an MLP neural net using Backpropagation as a learning algorithm, employed as a classifier in an Optical Character Recognition (OCR) application. Also, the process for determination of a set of optimal parameters describing the characters that conform each class is described. The processing and analysis of the images in BMP, GIF, JPG and TIF format are included. A comparative study of the possibilities of improvement of the learning process of an MLP net employing heuristics for its design and training is made. As a fundamental result a substantial improvement of the net learning process is obtained and an OCR of great reliability is built.