Title: Fuzzy system for image defect detection based on machine vision

Authors: Yiqiang Lai; Yongjun Qi; Xianfeng Zeng

Addresses: South China Business College, Guangdong University of Foreign Studies, Guangzhou, Guangdong, 510545, China ' Faculty of Megadate and Computing, Guangdong Baiyun University, Guangzhou, Guangdong, 510450, China ' South China Business College, Guangdong University of Foreign Studies, Guangzhou, Guangdong, 510545, China

Abstract: With the continuous upgrading of the industrial field, the market's requirements for product quality are also increasing, which requires more accurate product monitoring equipment. This paper analyses the composition of the vision system, and compares the collected images with the defects under manual detection based on the non-local mean denoising algorithm, and the results meet the system requirements. The experimental results show that the image size is 140*141, the distortion rate is 0.992, the image size is 120*81, and the distortion rate is 0.703. This means that the larger the image size, the higher the distortion. Before the improved algorithm, a total of 47 defects were detected, while after the improved algorithm, a total of 83 defects were detected. It can be seen that when the algorithm is improved, the number of defect detections increases significantly.

Keywords: machine vision; image processing; image defect detection; fuzzy systems.

DOI: 10.1504/IJMTM.2024.139490

International Journal of Manufacturing Technology and Management, 2024 Vol.38 No.4/5, pp.342 - 360

Received: 21 May 2022
Accepted: 05 Sep 2022
Published online: 03 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article