An OCR System for Numerals Applied to Energy Meters

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.