摘要
本文提出了利用机器视觉方法代替人工实现对车轮加工过程中字符的识别。使用自研激光轮廓传感器,基于OpenCV对图像进行预处理,对字符进行分割、归一化等操作,实现对字符字型的多次识别。实验表明:识别准确率达98.80%,具有识别准确率高、效率高等优点。
A method of using machine vision to replace the manual recognition of characters during wheel processing is proposed.A self-developed laser contour sensor is used to pre-process the image based on OpenCV,to segment and normalize characters,and to recognize the character font multiple times.Experiments show that the recognition accuracy is 98.8%,and the recognition accuracy is high and the efficiency is high.
作者
马晓欢
郭阳宽
张晓青
MA Xiaohuan;GUO Yangkuan;ZHANG Xiaoqing(Beijing Information Science and Technology University,School of Instrument Science and Opto Electronics Engineering,Beijing 100192)
出处
《智能建筑与工程机械》
2019年第3期67-68,共2页
Intelligent Building and Construction Machinery
关键词
机器视觉
动态识别
字符分割
模板匹配
machine vision
dynamic recognition
character segmentation
template matching
