Low-cost fabric flaw detection system and method

Abstract

The invention discloses a low-cost fabric defect detection system and method, and the system comprises an image processing module which carries out the pixel and neighborhood transformation of an area in the visual angle range of a camera, and converts a time domain signal into a frequency domain signal; the flaw detection module is used for calling the trained yolov5 model to detect flaws in real time and outputting a detection result; and the defect analysis module is used for judging whether alarm information is output or not and obtaining a cloth inspection result. The detection method comprises the steps of image collection and model training; preprocessing the to-be-detected image; performing flaw detection on the detection model, and synchronously creating a fabric defect database; and feeding back a detection result. The problems that a traditional camera is low in resolution, and detection equipment cannot distinguish common flaws from fatal flaws are solved, labor force is effectively utilized, and the production cost is reduced; and a fabric defect database is synchronously established, and training data is collected in the detection process, so that model detection is more accurate.

Description

technical field [0001] The invention relates to a defect detection system and method, in particular to a low-cost fabric defect detection system and method. Background technique [0002] The automatic fabric defect detection technology can automate the entire fabric inspection process. The current automatic inspection system mainly uses industrial cameras or infrared inspection equipment to detect large and small defects in the fabric and alarm and stop the fabric to realize real-time inspection of fabric defects. detection. On the one hand, fabric defect detection that relies on industrial cameras or infrared detection equipment greatly increases the manufacturing cost of the detection equipment; The precision and accuracy of defect detection have a certain impact; at the same time, these professional inspection equipment pays too much attention to the accuracy of cloth inspection, which will cause alarms or shutdowns for subtle defects, making workers need to rework many ...

AI Technical Summary

Problems solved by technology

On the one hand, the detection of fabric defects that relies on industrial cameras or infrared detection equipment greatly increases the manufacturing cost of the detection equipment; The precision and accuracy of defect detection have a certain impact; at the same time, these professional testing equipment pay too much attention to the accuracy of cloth inspection, resulting in alarms or shutdowns for subtle defects, making workers need to rework many times, which will reduce worker efficiency and increase inspection. The workload of cloth workers cannot reduce labor costs

Due to the high hardware cost of the existing intelligent testing equipment on the market and the limitation of defect detection technology, there are still a large number of enterprises still adopting the method of manual cloth inspection. However, the traditional manual inspection method has the disadvantages of low detection rate, Slow speed, high cost and many other problems

Images