[1]杜晓辉,刘霖,张静,等.火花塞端面缺陷自动检测算法设计[J].计算机技术与发展,2019,29(02):172-176.[doi:10．3969/j．issn．1673－629X．2019．02．036]
　DU Xiaohui,LIU Lin,ZHANG Jing,et al.Optoelectronic Inspection of Defects for Surface of Spark Plug[J].,2019,29(02):172-176.[doi:10．3969/j．issn．1673－629X．2019．02．036]
点击复制

火花塞端面缺陷自动检测算法设计()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年02期
页码:
172-176
栏目:
应用开发研究
出版日期:
2019-02-10

文章信息/Info

Title:
Optoelectronic Inspection of Defects for Surface of Spark Plug
文章编号:
1673－629X(2019)02－0172－05
作者:
杜晓辉; 刘霖; 张静; 倪光明; 刘娟秀; 刘永
电子科技大学 光电科学与工程学院，四川 成都 610054
Author(s):
DU Xiao－hui; LIU Lin; ZHANG Jing; NI Guang－ming; LIU Juan－xiu; LIU Yong
School of Optoelectronic Science and Engineering，University of Electronic Science and Technology of China，Chengdu 610054，China
关键词:
图像处理; 缺陷检测; 机器学习; 火花塞端面; 逻辑回归
Keywords:
image processing; defect detection; machine learning; end face of spark plug; logistic regression
分类号:
TP751.1
DOI:
10．3969/j．issn．1673－629X．2019．02．036
摘要:
对火花塞端面缺陷进行检测时，传统的检测方法是采用人工目测，检测精度低，受人为的影响因素多。根据火花塞端面检测的实际需求，设计了一种基于机器视觉的全自动检测算法。该算法首先利用图像形态特征采用改进的霍夫变换方法提取待检测圆环区域，并根据实际检测需求对圆环区域做极坐标变换，使圆环区域展开为矩形。然后采用局部阈值分割方法对其进行二值化，并利用形态学滤波的方法分离缺陷及类缺陷杂质区域，结合连通域标记算法提取缺陷及类缺陷杂质区域。最后，计算统计缺陷及类缺陷杂质的梯度直方图特征并对其进行逻辑回归分类识别。实验结果表明，该算法检测精度达到 99%，漏检率仅 1/500。不仅可完全满足工业生产的检测质量需求，而且检测周期为 0．6 s，满足了工业在线生产的速度需求。
Abstract:
When detecting the defect of spark plug end face，the traditional detection method is human visual inspection，which has low detection accuracy and is affected by many man－made factors． According to the actual requirements of spark plug end face detection，we design an automatic detection algorithm based on machine vision． The algorithm extracts the region of interests，that is，ring region，via theshape feature of the image with the way of improved Hough method firstly． And polar coordinate conversion has been taken to expand thering to a rectangle area according to the actual needs of the detection． To segment the image，the local－threshold method is applied，thenthe morphological filtering method is to isolate defects and defect type impurity region，extracting them by connected component labeling．Finally，to extract impurities and defects，gradient histogram characteristics are collected and classified by logistic regression． The experiment shows that the detection accuracy of the proposed algorithm has reached to 99%，while only 1/500 missed． The algorithm can notonly fully meet the needs of the testing quality of industrial production，but the speed of the production line with the cycle 0．6 s．

相似文献/References:

[1]李雷 张建民.一种改善的基于支持向量机的边缘检测算子[J].计算机技术与发展,2010,(03):125.
　LI Lei,ZHANG Jian-min.An Improved Edge Detector Using the Support Vector Machines[J].,2010,(02):125.
[2]张艳丽 保文星.粒子群优化算法在图像边缘检测中的研究应用[J].计算机技术与发展,2009,(05):26.
　ZHANG Yan-li,BAO Wen-xing.Research and Application of Image Edge Detection Based on PSO Algorithm[J].,2009,(02):26.
[3]詹金兰 李翠华.模拟实验系统的可视化研究[J].计算机技术与发展,2009,(05):228.
　ZHAN Jin-lan,LI Cui-hua.Visualization Research on Simulation Experiment System[J].,2009,(02):228.
[4]张燕 刘春.基于圆心定位的瓶口三圆周快速缺陷检测算法[J].计算机技术与发展,2009,(06):243.
　ZHANG Yan,LIU Chun.A Rapid Defect Detecting Algorithm of Bottle＇s Rim Based on Central Location and Three- Circle Method[J].,2009,(02):243.
[5]张家栋 张强 霍凯.图像处理在轴承荧光磁粉探伤中的应用研究[J].计算机技术与发展,2009,(08):216.
　ZHANG Jia-dong,ZHANG Qiang,HUO Kai.Study on Application of Image Processing in Bearing Fluorescent Magnetic Detection[J].,2009,(02):216.
[6]王文豪 张亚红 朱全银 单劲松.QR Code二维条形码的图像识别[J].计算机技术与发展,2009,(10):123.
　WANG Wen-hao,ZHANG Ya-hong,ZHU Quan-yin,et al.Image Recognition in 2 - D Bar Code Based on QR Code[J].,2009,(02):123.
[7]李孟歆 吴成东.粗糙集理论在图像处理中的应用[J].计算机技术与发展,2009,(03):208.
　LI Meng-xin,WU Cheng-dong.Rough Set Theory and Its Applications in Image Processing[J].,2009,(02):208.
[8]武彬.一种离焦模糊图像的复原方法[J].计算机技术与发展,2008,(01):74.
　WU Bin.A Method of Defocus Blurred Image Restoration[J].,2008,(02):74.
[9]蒋恩松 肖辉军 孙刘杰 熊清廉.基于机器视觉的套印误差自动检测系统设计[J].计算机技术与发展,2008,(07):173.
　JIANG En-song,XIAO Hui-jun,SUN Liu-jie,et al.Design of Automatic Detecting Printing Registration Deviation System Based on Machine Vision[J].,2008,(02):173.
[10]汪继文 林胜华 沈玉峰 邱剑锋.一种基于各向异性扩散的图像处理方法[J].计算机技术与发展,2008,(08):98.
　WANG Ji-wen,LIN Sheng-hua,SHEN Yu-feng,et al.An Approach for Image Restoration Based on Anisotropic Diffusion[J].,2008,(02):98.

更新日期/Last Update: 2019-02-10