【摘要】 针对目前锂电池极片表面存在亮度不均、低对比度微小缺陷难以检测的问题，提出了一种基于小波增强与Canny算法融合的锂电池极片缺陷检测方法。首先使用K-近邻均值滤波抑制图像背景噪声，然后基于小波变换分别采用线性调整和多尺度细节增强方法处理图像的低高频分量，进行图像增强，接着利用PSO-OTSU算法自适应获取增强后图像的最佳高低阈值，最后利用哈夫检测法连接边缘点。通过测试漏金属、亮点、划痕、孔洞等缺陷各700张图片，定量分析比较了3种算法的准确率，实验结果表明，相对于其他两种算法，本文算法可以较好地保留缺陷边缘细节，检测低对比度微小缺陷，提取精确完整的缺陷轮廓，检测准确率达97.85%,具有一定的实用价值。更多还原

【Abstract】 Current methods have limitations in detecting the uneven brightness and low contrast micro defects on the surface of the lithium battery electrode. To solve this problem, a algorithm based on the fusion of wavelet enhancement and the Canny operator was proposed. Firstly, the K-nearest mean filter algorithm was introduced to suppress the image background noise. Afterward, wavelet transform was implemented to separate the low-frequency and high-frequency components of the image. Subsequently, linear adjustment was adopted to process the low-frequency components, while the multi-scale detail enhancement method was used to process the high-frequency. Then PSO-OTSU adaptive algorithm was used to obtain the best threshold of the enhanced images. Finally, the Hough test was performed to connect the edge points. Through test defects such as leakage of metal, bright spots, scratches, holes each 700 images, the accuracy of quantitative analysis and comparison of 3 kinds of algorithm, experimental results show that compared with other algorithms, this algorithm had a detection accuracy of 97.85% and better performance in retaining the details of the defect edge, detecting low-contrast and micro defects, and extracting the defect contour.更多还原