摘要
为提高线路板缺陷的自动检测能力,结合图像处理技术,提出了线路板缺陷的图像检测方法。该方法首先对Gerber文件解析,获取标准线路板图像;其次利用定位孔检测实现标准线路板图像与待检测图像的配准;然后结合形态学滤波,完成线路板缺陷区域定位;最后根据常见缺陷的特征,综合采用面积法、连通域法和缺陷边缘邻域法,实现了常见缺陷类型的自动识别。通过对真实线路板图像仿真缺陷的检测实验,其结果证明了该方法的有效性。
In order to improve the automatic defect detection ability of printed circuit board（PCB）,a detection method for PCB defect based on image is proposed by combining image processing technology.For this method,the Gerber file is parsed firstly to get standard PCB image.Next,the registration of standard circuit board image and determined image is achieved by detecting the location of holes.Then,combining with morphological filtering,PCB defect area detection can be completed.Finally,according to the characteristics of common defects,by using area method,connected domain method and defect edge neighbor method,the automatic identification of defect types is realized.Simulations of defect detection in real PCB images demonstrate the effectiveness of this algorithm.
出处
《半导体光电》
CAS
CSCD
北大核心
2012年第2期303-306,共4页
Semiconductor Optoelectronics
基金
国家自然科学基金项目(61163047)
江西省工业支撑计划项目(2010GB00405)
关键词
印刷线路板
定位孔检测
缺陷检测
缺陷识别
printed circuit board
holes detection
defect detection
defect identification
