Polypropylene film defect detection method, equipment and medium

Through multimodal image processing methods, combined with feature extraction and attention calculation of visible light and infrared images, the problems of insufficient detection stability and generalization ability in polypropylene film inspection are solved, efficient and accurate film defect detection and positioning are achieved, and the intelligent level of industrial quality control is improved.

CN120689273APending Publication Date: 2025-09-23WUYI UNIV
0 Cites 2 Cited by

Patent Information

Application Number
CN202510611408.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-13
Publication Date
2025-09-23

AI Technical Summary

Technical Problem

Existing technologies for polypropylene film defect detection are limited by lighting variations, material differences, and the diversity of defect types, resulting in insufficient detection stability and generalization capabilities, and making it difficult to adapt to industrial detection needs where abnormal samples are scarce.

Method used

A multimodal image processing method is adopted, combining visible light and infrared images, and defect detection and positioning are performed through multi-scale feature extraction, channel attention and spatial attention calculation. Unsupervised learning is used to construct an image dataset, eliminating the dependence on labeled abnormal samples.

Benefits of technology

It achieves efficient and accurate thin film defect detection, improves detection efficiency and accuracy, reduces missed detection rate and false detection rate, and enhances the intelligent level of industrial quality control.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The embodiment of the invention provides a polypropylene film defect detection method, equipment and a medium. The method comprises the following steps: screening normal samples in a polypropylene film image to construct an image data set; extracting multi-scale features of the polypropylene film image; performing channel attention and space attention calculation on the multi-scale feature to obtain a first feature; performing channel conversion on the first features of different scales to obtain second features of the same channel; performing nonlinear transformation and local spatial feature extraction on the second feature to obtain a third feature; performing defect detection and defect positioning according to the third feature to obtain a detection result; the prior that a large number of defect samples are needed in traditional detection is eliminated, and efficient defect detection can be achieved after learning of a large number of normal samples.
Need to check novelty before this filing date? Find Prior Art