一种包装卷材快速在线检测算法

A Fast Online Detection Algorithm for Packaging Coils

目的提高包装卷材图像的检测速度与精度,以实现快速在线检测。方法预先对几副标准样本图像进行拼接,将得到拓展的样板图像作为动态模板的母版。检测过程中,首先计算待测图样中心区域经简化的图像几何矩,并在前述样板中的一段区间内搜寻最佳匹配位置。再以该位置为中心,在样板图像上划分出与待测图样相同大小的区域作为动态模板,最后利用图像差影法实现缺陷检测与识别。结果二阶简化几何矩能有效减少运算量,动态模板可显著提高卷材图像检测速度,以电子元器件包装卷材载料带为检测对象对所提出的方法进行了测试,在较高分辨率条件下检测速度不低于2 m/s。结论该算法可满足包装卷材快速在线检测需求,对提高相位不确定性图像检测速度有一定参考意义。

The work aims to improve the detection speed and accuracy of the packaging coil image to achieve the rapid online detection. A few standard image samples were spliced beforehand. The extended image samples obtained were taken as the master mask of the variable template. A simplified image geometric moment in the central region of the image sample to be detected should be calculated first during the detection, and the best matching position was searched in a section of the foregoing template. Then, with such position as the center, the area marked off on the template image having the same size as the image to be detected was regarded as the variable template. Finally, the image subtraction method was implemented to realize the detection and recognition of defects. The two-order simplified geometric moments could reduce the operand effectively, and the dynamic template could significantly improve the detection speed of the coil image. The proposed algorithm was tested with the packaging coil carrier tape of the electronic components as the detected objects. The detection speed was no less than 2 m/s under the condition of higher resolution. The proposed algorithm can meet the requirements of rapid online detection of packaging coil, and provide certain reference significance for the detection speed of uncertain-phase image.