基于漫水填充与环形校正结合的极耳缺陷检测

Defect detection of tab ear based on the combination of flood filling and ring correction

为了实现锂电池极耳缺陷自动化检测,提出了一种基于漫水填充与环形校正结合的锂电池极耳缺陷检测算法。采用分段线性变换进行图像预处理;使用漫水填充算法分割极耳缺陷图像,利用形态学处理去除雪花噪声;通过Canny算子获取极耳缺陷轮廓边缘,在计算极耳缺陷关键参数的基础上,提出环形校正方法对关键参数进行修正,以实现缺陷的准确检测。为了验证该算法的检测性能,选取2 000个样本进行测试。实验结果表明,该算法能够准确检测多种极耳缺陷,检测准确率平均值为99.45%。

In order to realize the automatic detection of the defects of the lithium battery tabs,a detection algorithm for the tabs of the lithium battery based on the combination of flood filling and ring correction is proposed.First,segmentation linear transformation is used for image pretreatment.The flood filling algorithm is used to segment the image of the ear defect,and snowflake noise is removed by morphological processing.The contour edge of the ear defect is obtained by the Canny operator.Finally,based on the calculation of the key parameters of the ear defect,a ring correction method is proposed.The parameters are modified to achieve accurate detection of defects.In order to verify the detection performance of the algorithm,2000 samples were selected for testing.The experimental results show that the detection algorithm of the lithium battery tab ear defects in this paper can accurately detect a variety of tab ear defects,and the average detection accuracy rate is 99.45%.