Unsupervised industrial product defect detection method and device based on deep learning

Abstract

The invention discloses an unsupervised industrial product defect detection method and device based on deep learning, and a computer readable storage medium. The method comprises the following steps:training a first auto-encoder through employing a training sample, and obtaining an implicit expression of the training sample in a training process; carrying out dimension reduction processing on theimplicit expression of the training sample to obtain an implicit expression of a normal sample; initializing a memory module in a second auto-encoder by using the implicit expression of the normal sample, and training the second auto-encoder by using the training sample; inputting the test sample into the trained second auto-encoder to obtain a reconstructed sample; and calculating by using the test sample and the reconstructed sample to obtain a defect mask, and judging whether the test sample has defects or not according to the defect mask. According to the invention, defects can be effectively detected under the condition that only defect-free image samples are used for training the model, and the defect detection effect is improved.

Description

technical field [0001] The present application relates to the technical field of defect detection, in particular to a method and device for unsupervised defect detection of industrial products based on deep learning, and a computer-readable storage medium. Background technique [0002] In the production process of industrial products, due to the limitation of technological level and the influence of environmental factors, defective products will inevitably be produced. If this part of the product cannot be detected at the source of the defect as soon as possible, it will flow into the subsequent production steps, which will increase the difficulty of subsequent detection and increase the cost of repair. What's more serious is that if these products accidentally enter the market for sale, it will have a great impact on the product image. In order to detect these defective products, the traditional technology adopts the method of deploying AOI (Automatic Optic Inspection, aut...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a deep learning-based unsupervised industrial product defect detection method and device, and a computer-readable storage medium, which solves the problem of poor defect detection results caused by the difficulty of obtaining defective image samples in traditional technologies, and realizes In order to effectively detect defects when only using non-defective image samples to train the model, the effect of defect detection is improved

Images