基于图像处理的电子元器件表面缺陷检测技术

作者：郑秀莲1，袁巧玲2，沈亚琦2 日期：2009-08-18/span> 浏览：3761 查看PDF文档

基于图像处理的电子元器件表面缺陷检测技术

郑秀莲1，袁巧玲2，沈亚琦2
（1.浙江工业大学浙西分校 信电系，浙江 衢州 324000; 2.浙江工业大学 机械制造及自动化教育部重点实验室，浙江 杭州 310014）

摘要：针对电子元器件的表面缺陷对其性能和品质有直接影响的问题，基于图像处理技术，以晶振外壳缺陷的检测为例，研究了电子元器件表面缺陷的检测技术。首先建立了检测系统平台，然后对所获取的图像进行分析和检测目标分割,并由生成的灰度共生矩阵计算纹理特性值。基于惯性值对纹理的深浅具有敏感性,比较研究之后，采用了惯性值作为检测表面缺陷的指标。试验结果表明该方法能够有效检测平面缺陷。
关键词：表面检测；晶振外壳;图像处理;纹理特征
中图分类号：TP274+.5文献标识码：A文章编号：1001-4551(2009)07-0014-03

Electronic components surface defects detecting technology based on image processing
ZHENG Xiu-lian1, YUAN Qiao-ling2, SHEN Ya-qi2
(1. Department of Information and Electrical Engineering, West Branch of Zhejiang University of Technology, Quzhou 324000, China;
2. The MOE Key Laboratory of Mechanical Manufacture and Automation, Zhejiang University of Technology, Hangzhou 310014, China)
Abstract: Aiming at the Influence of electronic components surface quality for its properties and performance, surface defect detection technology was researched based on image processing technology, and the detection of crystal oscillators shell was used as an example. Firstly, the detection system platform was set up. Then, the treatment of acquainting images was fulfilled and grayscale co-occurrence matrix was generated. Because the inertia value is sensitive to the depth of the texture, after the comparative study of the value of texture characteristic, the inertia value was selected as the target of identification of the crystal surface defects. The research results show that this method can effectively detect planar defects.
Key words: surface defects; crystal oscillators shell; image processing; texture characteristic
参考文献(References):
［1］牛付林.超声波检测技术在保证电子元器件质量中的应用［J］.电子质量，2003(9)：8-10.
［2］王永强，于德敏，许增扑.机器视觉玻壳缺陷检测方法的研究［J］.天津轻工业学院学报，2001(2)：9-12.
［3］吴平川，路同浚，王炎.机器视觉与钢板表面缺陷的无损检测［J］.无损检测，2000，22(1)：13-16.
［4］牛玉洲，宋培华，张建正.机器视觉在铜箔基板疵点在线检测系统中应用［J］.微计算机信息，2001，17(11)：44-45.
［5］费耀平，谷士文，刘应龙.工业视觉系统及应用［J］.长沙铁道学院学报，1997，15(1)：25-30.
［6］［美］赫恩，蔡士杰，宋继强，等.计算机图像学［M］.3版.北京：电子工业出版社，2005.
［7］REED T R, DUBUF J M H. A review of recent texture segmentation and feature extraction techniqure［J］.CVGIP:Image Understanding,1993,57(3):359-372.