Metallographic structure intelligent identification method based on neural network

The invention discloses an intelligent metallographic structure recognition method based on a neural network, and relates to the technical field of metal image recognition, and the technical scheme is characterized in that the method comprises the following steps: S1, image quality detection; s2, labeling metallographic structure images, wherein multi-structure labeling is adopted; s3, constructing a metallographic structure image data set; s4, cleaning training data, and randomly extracting part of data in the data set as a training set for training; and S5, performing ResNet network training, and outputting an identification result. According to the intelligent metallographic structure recognition method based on the neural network, subjective errors caused by manual evaluation are avoided, the analysis result is more objective and accurate, repeated work of experts can be reduced, the defect of experienced metallographic analysts is overcome, and the intelligent metallographic structure recognition method