Semi-supervised industrial product flaw detection method and system based on positive sample learning

Abstract

The invention discloses a semi-supervised industrial product flaw detection method and system based on positive sample learning. The method comprises the following steps: training an image restoration network and a flaw segmentation prediction network through positive sample images; and inputting an image containing a flaw to be detected into the image restoration network to obtain a restored certified product image, calculating an absolute value of a difference value between the two images, splicing the three images to obtain a detection tensor, generating a segmentation mask binary image according to the detection tensor through the segmentation prediction network, and obtaining a flaw region. According to the method, a semi-supervised deep learning method is used, defect position data of a pixel level does not need to be labeled in advance, the labeling problem in defect segmentation is solved, and full-automatic training learning, defect segmentation and defect classification can be realized only by using part of certified product images in production. And pixels at various types of abnormal flaw positions can be segmented.

Description

technical field [0001] The present invention relates to a technology in the field of image processing, specifically a method and system for detecting defects of semi-supervised industrial products based on positive sample learning, such as steel products, printed paper products, and cloth textiles. Background technique [0002] In industrial production, due to various reasons, there will be various defects, such as pollution, incompleteness, scratches, holes. There are many kinds of defects and complex shapes, so it is difficult to identify them with the naked eye. It is often necessary for inspectors to manually judge and screen defective products on the production line. Existing defect detection requires workers to judge the quality of each sample at close range under high light conditions, which puts a high burden on vision, the recognition process is unstable and easily affected by other factors, and the production efficiency is low. With the development of artificial ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned deficiencies in the prior art, the present invention proposes a semi-supervised industrial product defect detection method and system based on positive sample learning, using a semi-supervised deep learning method, without the need to mark pixel-level defect position data in advance, which solves the problem For the labeling problem in defect segmentation, only some genuine (positive sample) images in production can be used to realize fully automated training and learning, and perform defect segmentation and classification of whether there is a defect

Images