Defect detection method based on cyclic generative adversarial network and structural similarity

Abstract

The invention relates to a defect detection method based on a cyclic generative adversarial network and structural similarity, and the method comprises the following steps: S1, obtaining and preprocessing defect pictures, and enabling the defect pictures to serve as a training data set; s2, constructing a CycleGAN model, and training based on the training data set to obtain a model for mapping the defect picture into a defect-free picture; s3, inputting a to-be-detected image into the trained CycleGAN model, and comparing the difference between the original image and the repaired image by using a structural similarity algorithm to obtain a difference binary image; and S4, connected domain noise reduction and morphological processing are carried out on the difference binary image, and if the original image has defects, the white area in the binary image is the extracted defect shape. The method has the advantages of being high in detection precision, high in robustness to complex texture surfaces, capable of accurately detecting small defects and the like.

Description

technical field [0001] The invention relates to the field of machine vision and the field of industrial production, in particular to a defect detection method based on cyclic generative adversarial network and structural similarity. Background technique [0002] "Object detection" is one of the core problems in the field of computer vision (CV). Its task is to locate the desired target (object) from a given image or video, identify different targets, and output the category of the target. The application scenarios of target detection are very wide, among which face detection, pedestrian detection, vehicle detection, etc. are widely studied. Defect detection is a specific application of target detection, and the target to be detected is the possible defects on the surface of the product. Industrial defect detection has long been done manually. However, relying on manual detection of surface defects is time-consuming, laborious, and has strong subjective bias, and its effici...

AI Technical Summary

Problems solved by technology

However, the current deep learning methods for defect detection still have some shortcomings: 1. Most of them require training data with labels (image level or pixel level), and labeling a large amount of data is undoubtedly time-consuming, laborious and subjective; 2. The detection accuracy is not high Or the detection error rate is too high, it is difficult to meet the requirements of practical applications

[0003] Since industrial surface defect detection is still mainly done manually, there are problems such as high labor intensity, low efficiency, and great subjectivity, which cannot well meet the high efficiency and high precision requirements of industrial production, and most of the defects based on machine vision The detection method also has the disadvantages of requiring manual labeling of a large amount of training data, long training time, and poor detection effect on surfaces with messy textures.

Images