基于机器视觉的数字化仪表字符识别

Character Recognition of Digital Instrument Based on Machine Vision 

摘要:

针对工业生产中测试仪表显示数据的自动识别问题,提出一种基于机器视觉的数字仪表数据识别方法；文章方法利用图像获取、图像去噪、阈值分割、光学字符识别等技术有效远程识别LCD/LED显示的数字信息。通过实验验证,该系统能远程实时识别具有LCD/LED显示的数字化仪表的显示数据,识别率能达到99%以上,并且能够实现超限报警及数据保存功能。

Abstract:

In order to solve the problem of automatic identification display data of test instrument in industrial production, this paper put forward a digital instrument data recognition method based on machine vision. The method makes use of image acquisition, digital image denoising, threshold segmentation, optical character recognition technology to effectively identify LCD/LED display. Through the experimental verification, this system can real-time recognize the display data of remote digital instrument with LCD/LED display, the recognition rate can reach more than 99%, and can realize the alarm and data storage function.