首页 | 本学科首页   官方微博 | 高级检索  
     

基于改进模板匹配的在线钢坯标号识别方法
引用本文:张浩,蔡晋辉,才辉,周泽魁. 基于改进模板匹配的在线钢坯标号识别方法[J]. 计算机集成制造系统, 2007, 13(10): 2076-2080
作者姓名:张浩  蔡晋辉  才辉  周泽魁
作者单位:浙江大学,控制科学与工程学系工业控制技术国家重点实验室,浙江,杭州,310027;浙江大学,控制科学与工程学系工业控制技术国家重点实验室,浙江,杭州,310027;浙江大学,控制科学与工程学系工业控制技术国家重点实验室,浙江,杭州,310027;浙江大学,控制科学与工程学系工业控制技术国家重点实验室,浙江,杭州,310027
摘    要:为避免钢坯标号数字字符出现局部畸变、笔画断裂和粗细变化等现象,提出了一种新的基于改进模板匹配的在线实时识别方法.利用灰度面积滤波、改进二值化等图像处理技术滤除干扰,完成字符提取;通过投影法得到单个字符;引入隶属度概念,改进了经典模板匹配方法,以增强抗干扰能力.试验结果表明,该方法可行有效,稳定性和实时性均满足实际生产需要.

关 键 词:数字字符识别  模板匹配  自动视觉检测  钢坯标号
文章编号:1006-5911(2007)10-2076-05
收稿时间:2007-01-04
修稿时间:2007-04-02

On-line inspection method for steel billet characters based on improved template matching
ZHANG Hao,CAI Jin-hui,CAI Hui,ZHOU Ze-kui. On-line inspection method for steel billet characters based on improved template matching[J]. Computer Integrated Manufacturing Systems, 2007, 13(10): 2076-2080
Authors:ZHANG Hao  CAI Jin-hui  CAI Hui  ZHOU Ze-kui
Abstract:To avoid local distortion,stroke break and thickness variation in steel billets characters,a real-time online identification system based on improved template matching was proposed.Through image processing technique including grayscale area filter,improved auto-threshold algorithm,noises were filtered and characters were extracted from the image.Single character was achieved by using projection function.Classical template matching technique was improved by membership assignment conception to recognize characters robustly.Experimental results proved the feasibility and effectiveness of the system.Stability and real-time performance of the method were catering to production requirements.
Keywords:figure character recognition  template matching  automatic vision inspection  characters on steel billet
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号