Author(s)

Weibin Yan

Corresponding Author

Weibin Yan

Abstract

As an important production link, industrial product quality testing would determine the quality of the products produced and affects its market competitiveness. At present, in most product lines, product testing often relies on labor, which would not only cause high cost due to human input, but also often fail to ensure the accuracy of product testing. The development of computer vision technology has broken through the bottleneck of industrial product quality inspection. Therefore, in this paper, we propose a computer vision-assisted defect detection regression model, which can determine whether the industrial product is defective by extracting the image defect feature vector and performing regression fitting. The experimental results show that this method has high accuracy and has the value of popularization and application.

Keywords

Computer vision; Defect detection; Regression model