Surface defect detection method based on deep learning algorithm

The invention discloses a surface defect detection method based on a deep learning algorithm, solves the problem of sample imbalance when surface defect detection is carried out by adopting the deep learning algorithm in the prior art, and belongs to the technical field of detection in industrial production. The method comprises the following steps: establishing a surface defect classification model based on a deep learning algorithm, and training the surface defect classification model by using an initial training sample set D1; sampling various surface defect image samples in the D1 to obtain a balanced image sample set D2, continuing to train the surface defect classification model by using the D2, and in the training process, freezing parameters of a convolutional layer in the surface defect classification model and adjusting parameters of a full connection layer until the surface defect classification model converges; detecting a to-be-detected image sample by using the surface defect classification mode