论文部分内容阅读
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 detection ability of circuit board defects, the image detection method of circuit board defects is proposed in combination with image processing technology. The method firstly analyzes the Gerber file and obtains the standard circuit board image. Secondly, the registration of the standard circuit board image and the image to be detected is achieved by using the positioning hole detection. Secondly, the morphological filtering is performed to locate the defective area of the circuit board. Finally, Feature, a combination of area method, connected domain method and defect edge neighborhood method, to achieve a common type of automatic defect recognition. Through the real circuit board image simulation defect detection experiments, the results prove the effectiveness of the method.