Research on Visual Detection Method of Sound Film Broken Glue Defect

Jianchun Liu; Xunjin Jiang; Chaoqi Huang; Yuquan Lin

doi:10.5566/ias.3143

Authors

Jianchun Liu Xiamen University of Technology
Xunjin Jiang
Chaoqi Huang
Yuquan Lin

DOI:

https://doi.org/10.5566/ias.3143

Keywords:

Broken glue defect, Improved iteration, Maximum interclass variance method, Threshold segmentation

Abstract

Broken glue defect is a common defect in sound film dispensing. Aiming at the problem of fuzzy glue region boundary frequently occurring in the detection process, an improved iterative maximum interclass variance method was proposed to detect broken glue defects. Due to the skewness distribution of the gray curve of the sound film, the median value of the gray value of the image was replaced by the average value of the improved iterative method to eliminate the sound film. The initial threshold of the sound film dispensing region was quickly converged. The maximum inter-class variance method was combined to improve the extraction accuracy of the glue region boundary. The image features of single gap, multi gap, and dislocation defect types in qualified and broken products were compared, and the number and offset of glue areas were calculated to identify defects accurately. Fifteen thousand products were randomly selected on the production line for testing, and the results showed that the detection accuracy rate of qualified products was 100%, and the detection accuracy rate of broken glue was 99.1%, which met the needs of enterprises.

References

Chen SX, Wang T (2020). Vision-based quality inspection method for glue application[J]. Combined machine tool and automatic processing technology 7:138-141.

Guo YM, Wang Y, Meng K, Zhu ZN (2023). Otsu Multi-Threshold Image Segmentation Based on Adaptive Double-Mutation Differential Evolution[J]. Biomimetics (Basel) 8(5):418.

Guo YK, Zhu YC, Liu LP, Huang Q (2022). A review of research on image enhancement methods in the air-frequency domain[J]. Computer Engineering and Applications 58(11):23-32.

He XH, Chen CG, Zhou C, Xie DF, Xie Hw (2020). Dispensing quality inspection method based on machine vision[J]. Combined Machine Tools and Automated Machining Technology 0(11):99-101,106.

Huang P, Zheng Q, Liang C (2020). A review of image segmentation methods[J]. Journal of Wuhan University (Science Edition) 66(06):519-531.

Liao Y (2015). Design and realization of engine block gluing detection module based on machine vision [D]. Chengdu: University of Electronic Science and Technology.

Liang JL, Ye GL, Guo JW, Wu JX (2023). Research on visual inspection system for button battery defects[J]. Mechanical Design and Manufacturing 385(3):225-229.

Li ZC, Cao YP (2022). Leukocyte image segmentation method based on improved iterative thresholding[J]. Optics & Photonics Technology 20(02):84-94.

Ma W ,Li W ,Cao P (2019). Ranging Method of Binocular Stereo Vision Based on Random Ferns and NCC Template Matching[J]. IOP Conference Series: Earth and Environmental Science 252(2).

Shen JH , Wu XJ ,Wang XH, Liang GY (2023). Robust shape-based template matching algorithm for target localization under SEM.[J]. Optics express 31(20) :32652-68.

Yu YS, Su YF, Gao JS (2023). Algorithm for gluing quality detection based on KNN classification[J]. Combined Machine Tools and Automated Machining Technology 07:127-130.

Yu J, Cheng X, Zhao Z (2022). A machine vision method for measurement of drill tool wear[J]. The International Journal of Advanced Manufacturing Technology 118: 3303-14.

Zhang JG, Ji TT, Xin MX, Zuo CM, Liu J (2021). Edge extraction method in adhesive coating defect detection[J]. Ship Engineering 43(2):128-133.

Zou R, Dai WJ, Bai SH, Wu SL (2024). Edge-preserving light-field image super-resolution via feature affine transformation network[J]. OPT LASER ENG 172.