Automatic defect inspection system based on deep learning

摘要

generating N sub-images by dividing the image at regular intervals along a predetermined direction, generating input data for input to a feature extractor from the N sub-images, and inputting input data into the feature extractor to obtain an image Discloses a method comprising the step of extracting the features of. The dimension value of the dimension of the input data is one greater than the dimension value of the dimension of the comparison input data generated to be input to another feature extractor from the image in order to extract features of the image using another feature extractor composed of CNN.