基于机器视觉的软包锂电池表面缺陷检测

Surface defect detection of soft-pack lithium battery based on machine vision

针对软包锂电池表面缺陷检测,基于机器视觉技术提出了一种改进的自动检测方法。对图像进行预处理后,将Canny算子检测法和Close_Edges算子检测法相结合,分割出软包锂电池表面的缺陷;最后以最小外接矩形法计算出划痕的长度和宽度,以累加法计算出针孔的直径。实验结果表明该方法能够有效分割出软包锂电池表面的划痕和针孔,缺陷尺寸计算的误差低于5%。

An improved automatic detection method based on machine vision technology was proposed for detecting surface defects of soft-pack lithium batteries.After the image was preprocessed,the Canny operator detection method and the Close_Edges operator detection method were combined to segment the defects on the surface of the soft-pack lithium battery;finally,the length and width of the scratches were calculated by the minimum external rectangle method,and then the diameter of the pinhole was calculated by the accumulation method.Experimental results show that this method can effectively detect the scratches and pinholes on the surface of the soft-pack lithium battery,and the error of the defect size calculation is mostly within 5%.