Dirty filament defect detection method for packaged filaments

Abstract

The invention discloses a dirty filament defect detection method for a packaged filament. The method comprises the following steps: acquiring a plurality of acquired images of a to-be-detected area ofthe packaged filament; intercepting a target image corresponding to the detected position in the to-be-detected area in the acquired image; determining a suspected area in the target image, and obtaining gray feature parameters of the suspected area; determining an irregular geometric figure corresponding to the suspected area, and obtaining geometric feature parameters of the irregular geometricfigure; and determining whether the packaged filament has a dirty filament defect or not according to the gray feature parameters and the geometrical feature parameters. According to the dirty filament defect detection method for the packaged filament, the error rate of manual visual inspection can be reduced, the detection efficiency is improved, and the production cost can be saved.

Description

technical field [0001] The invention relates to the technical field of surface detection of packaged filaments, in particular to a detection method for dirty filament defects of packaged filaments. Background technique [0002] The packaged filament is a packaged product with a certain shape and capacity made by the filament through a winding mechanism during the production process. The defects of packaged filaments are mainly divided into two parts: physical and chemical property defects of filaments and appearance defects of packaged filaments. Through practical production, it is found that the appearance defects of packaged filaments have an extremely important impact on the quality of the fabric, which will lead to a decrease in the yield of the fabric. Therefore, in the production process, it is necessary to strengthen the detection of appearance defects of packaged filaments. [0003] The dirty filament of the packaged filament is caused by the contamination of the p...

AI Technical Summary

Problems solved by technology

[0004] Due to the deformability, multi-curved surface, and large inspection surface of packaged filament, it is difficult to extract uniform standards for its appearance defect characteristics. The appearance inspection of packaged filament has always affected the realization of intelligent manufacturing in the long production process. Defect detection of soiled silk by manual visual inspection

[0005] Although the detection of soiled silk defects by manual visual inspection can detect some defects, the manual visual inspection method will increase the labor cost of production, and there is no unified and strict quality standard, so it is difficult to guarantee the accuracy of the detection results

Images