Lead frame surface defect detection method and system, storage medium and terminal

The invention discloses a lead frame surface defect detection method and system, a storage medium and a terminal, and belongs to the technical field of lead frame detection, through a defect judgment mode of extracting an array unit image and a pixel value of the array unit image, the image inclination resistance is high, and therefore the accuracy of defect detection is improved; the defect segmentation is realized by adopting the neural network based on the improved Unet, the detection rate of weak targets which are difficult to identify by naked eyes is very high, and the defects are accurately positioned; and finally, performing grade judgment on the defects through a deep learning method, thereby removing the work of manual re-judgment required after detection, and improving the re-judgment efficiency. 本发明公开了一种引线框架表面缺陷检测方法、系统、存储介质及终端，属于引线框架检测技术领域，通过提取阵列单元图像及其像素值的缺陷判断方式，抗拒图像倾斜能力较强，从而提高了缺陷检测的准确性；通过采用了基于改进Unet的神经网络实现了缺陷的分割，对于肉眼难以辨识，弱小的目标具有很高的检出率，对缺陷进行准确定位；最后通过深度学习的方法对缺陷进行等级判定，从而去除检测后需要的人工复判的工作，提高复判效率。