基于机器视觉的油画棒检测系统的设计
DOI:
CSTR:
作者:
作者单位:

1.上海理工大学光电信息与计算机工程学院 上海 200093;2.上海电缆研究所 上海 200093

作者简介:

通讯作者:

中图分类号:

TN202

基金项目:

上海市自然科学基金(15ZR1417400)、国家自然科学基金青年基金(61302181)资助项目


Design of oil painting stick detection system based on machine vision
Author:
Affiliation:

1.School of Opticalfor Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China; 2.Shanghai Electric Cable Research Institute,Shanghai 200093, China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    油画棒装盒传统方式采用人工,针对其摆放效率低、成本高的问题,设计了基于机器视觉的油画棒装盒系统,选用ARM芯片做图像处理,在有限的资源配置和时间条件下完成任务。系统通过摄像头对油画棒进行图像采集,控制电机转动油画棒,进行图像匹配,完成投放。系统先对图像定位、选取,滤波去噪,再采用改进的自适应阈值的直方图匹配算法,并结合模板图像和待匹配图像的相关系数,有效降低了计算量,提高了系统的识别率。实践证明系统的工作稳定,能实现对油画棒角度的有效调整,匹配速度快,单台识别率达到99%以上,能完成产品的自动装配。

    Abstract:

    The traditional way of oil painting stick packing is artificial.In order to solve the problem of low efficiency and high cost, this paper designs the system based on machine vision. The ARM chip is chosen as coreof the image processing system,under the condition of limited resource and time. The system collects the image through the camera, controls the motor to rotate the oil painting stick, carries on the image matching, completes delivers. The system first locates, selectsthe image and filters to denoise the image. Thenthe system uses the improved histogram matching algorithm of adaptive threshold, and combines the correlation coefficient between the template image and the image to be matched, which effectively reduces the computation and improves the recognition rate of the system. Practice shows that the work of the system is stable, can achieve the effective adjustment of the angle of the oil paintingwith a high matching speed.The recognition rate of thesystem is above 95%.The system can complete the automatic assembly of products.

    参考文献
    相似文献
    引证文献
引用本文

王祖德,张大伟,杨海马,涂建坤,姚龙隆.基于机器视觉的油画棒检测系统的设计[J].电子测量技术,2017,40(7):121-125

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2017-08-15
  • 出版日期:
文章二维码