Um Sistema de OCR para Algarismos aplicado em Medidores de Energia (An OCR System for Numerals Applied to Energy Meters)

Auzuir Ripardo de Alexandria (auzuir@gmail.com)1, Paulo César Cortez (cortez@deti.ufc.br)2, John Hebert da Silva Felix (johnfelix@unilab.edu.br)3, Tibério Menezes de Oliveira (tiberiobenfica@gmail.com)4, Anaxágoras Maia Girão (anaxa@ifce.edu.br)4, João Batista Bezerra Frota (jb@ifce.edu.br)4, Jéssyca Almeida (Jessyca Bessa )1


1Programa de Pós-graduação em Engenharia de Telecomunicações, Instituto Federal de Educação, Ciência e Tecnologia do Ceará - IFCE
2Universidade Federal do Ceará - UFC
3Universidade da Integração Internacional da Lusofonia Afro-Brasileira - UNILAB
4Instituto Federal de Educação, Ciência e Tecnologia do Ceará - IFCE

This paper appears in: Revista IEEE América Latina

Publication Date: Sept. 2014
Volume: 12,   Issue: 6 
ISSN: 1548-0992


Abstract:
This work describes a prototype of an OCR (Optical Character Recognition) system designed for reading digits of power measurement devices, using Artificial Neural Networks. The motivation for this work is the implementation of an alternative automatic measurement system to be used in a prepaid power system - SEPPRA. Prototype software using Computer Vision techniques and pattern recognition through Neural Networks is implemented in the C++/Windows platform. Considering this application, adaptive threshold methods are compared in order to choose the more appropriated algorithm of binarization. Several algorithms are implemented and evaluated under different conditions of zoom and camera focus. The system works satisfactorily and can be carried to other platforms, making possible its production in commercial scale.

Index Terms:
OCR, Neural Networks, Computer Vision, adaptative thresholding   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (449)]