检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:张银 吕彦明 钱云杰 ZHANG Yin;LYU Yanming;QIAN Yunjie(School of Mechanical Engineering,Jiangnan University,Wuxi 214122,China)
出 处:《自动化仪表》2023年第5期46-50,55,共6页Process Automation Instrumentation
摘 要:为了实现工业仪表的自动化识别检验、降低人力消耗,应用机器视觉和图像处理技术对数字仪表自动读数识别进行研究。对采集的字符图像进行一系列预处理,包括灰度化以及采用双边滤波算法对含有背景的图像进行图像降噪预处理。提出了1种针对数字仪表字符区提取及快速识别的算法。基于透视变换以及轮廓提取函数实现仪表字符区的倾斜校正及快速提取,并对提取的字符进行形态学处理。提出了1种改进的穿线法对未进行字符分割处理的图片进行识别,并针对字符1的特征提出了快速识别方法。该算法省去了字符分割的时间,提高了字符识别效率。试验证明,算法对数码管的识别正确率达到99.3%、单幅图片识别时间为6.95 ms,可有效应用于计量、检验等数显仪表识别场合,提高检验效率。In order to realize the automatic identification and inspection of industrial meters and reduce human consumption,machine vision and image processing techniques are applied to investigate the automatic reading recognition of digital meters.A series of preprocessing is performed on the acquired character images,including grayscale and image noise reduction preprocessing for images containing backgrounds using bilateral filtering algorithms.An algorithm is proposed for the extraction and fast recognition of character areas of digital meters.Based on perspective transformation and contour extraction function to achieve tilt correction and fast extraction of instrument character areas,and morphological processing of the extracted characters.An improved threading method is proposed to recognize the images without character segmentation processing,and a fast recognition method is proposed for the characteristics of character 1.The algorithm eliminates the time of character segmentation and improves the efficiency of character recognition.The test proves that the algorithm achieves 99.3%correct recognition rate for digital tube and 6.95 ms recognition time for a single picture,which can be effectively used in the recognition of digital display instruments such as metrology inspection to improve the inspection efficiency.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.49