基于直方图数据拟合的PCB板嵌孔识别研究

 杨飞平,徐雷,贺云翔,李大双

(四川大学 制造科学与工程学院,四川 成都 610065)
摘要:快速精准地识别PCB板上感兴趣区域的位置,是图像处理过程中衡量算法有效性的重要指标。在图像处理的前期,通过分析同一背景条件下灰度曲线的变化趋势,确定光照不均匀对于PCB板感兴趣区域的影响,提出了运用同态滤波处理降低图像灰度变化的动态范围,从而加强感兴趣区域中目标和背景的对比度。基于现阶段相关PCB板的识别分割算法,针对研究对象PCB板实际感兴趣区域的灰度分布,探讨了全局阈值分割方法的优势。在此基础上,为了更精确的图像分割效果,提出了一种基于灰度直方图数据拟合的阈值分割方法。根据不同的阈值分割算法对图像进行处理,通过比较分析,结果表明本文提出的算法能够更加快速精确地分割出图像的感兴趣区域。
关键词:PCB板;灰度曲线;同态滤波;数据拟合;阈值分割;目标识别
中图分类号:TP391 文献标志码:A doi:10.3969/j.issn.1006-0316.2018.07.001
文章编号:1006-0316 (2018) 07-0001-07
Research on PCB Plate Hole Recognition Based on Histogram Data Fitting
YANG Feiping,XU Lei,HE Yunxiang,LI Dashuang
( School of Manufacturing Science and Engineering, Sichuan University, Chengdu 610065, China )
Abstract:Rapid and accurate identification of the region of interest(ROI) on the PCB  is an important indicator to measure the effectiveness of the algorithm in image processing. The paper focus on the influence of uneven illumination for PCB in the ROI through the analysis of variation trend of the gray curve in the same conditions in the early stage of image processing. The researchers proposed to use the dynamic range of homomorphic filtering to reduce the image gray level, so as to enhance the contrast of target and background in the ROI. Based on the relevant recognition and segmentation algorithm of PCB board at present stage, global threshold segmentation method shows some advantages in the gray distribution of the actual ROI of PCB object. On this basis, a threshold segmentation method based on gray histogram data fitting is proposed to obtain more accurate image segmentation results. The researchers carried out image processing with different threshold segmentation algorithms. Through comparative analysis, the results show that the algorithm proposed in this paper can segment the interested area of image more quickly and accurately.
Key words:PCB board;gray curve;homomorphic filtering;data fitting;threshold segmentation;target recognition
———————————————
收稿日期:2018-01-22
基金项目:四川省科技支撑计划资助项目(2016GZ0164);四川省经信委项目(2017ZB073)
作者简介:杨飞平(1991-),男,四川巴中人,硕士研究生,主要研究方向为机器视觉、工业机器人智能化集成应用系统;贺云翔(1992-),男,四川成都人,硕士研究生,主要研究方向为计算机辅助设计制造;李大双(1994-),男,四川绵阳人,硕士研究生,主要研究方向为机器视觉。*通讯作者:徐雷(1973-),女,吉林怀德人,博士,副教授,主要研究方向为数字化设计与制造、3D打印、智能制造等。
 

 

设为首页  |  加入收藏    |   免责条款
《机械》杂志版权所有     Copyright©2008-2012 Jixiezazhi.com All Rights Reserved 

  电话:028-85925070    传真:028-85925073    E-mail:jixie@vip.163.com

地址:四川省成都锦江工业开发区墨香路48号   邮编:610063

Powered by PageAdmin CMS