A Machine Vision Development Framework for Product Appearance Quality Inspection
-
Published:2022-11-14
Issue:22
Volume:12
Page:11565
-
ISSN:2076-3417
-
Container-title:Applied Sciences
-
language:en
-
Short-container-title:Applied Sciences
Author:
Zhu QiuyuORCID, Zhang YunxiaoORCID, Luan Jianbing, Hu Liheng
Abstract
Machine vision systems are an important part of modern intelligent manufacturing systems, but due to their complexity, current vision systems are often customized and inefficiently developed. Generic closed-source machine vision development software is often poorly targeted. To meet the extensive needs of product appearance quality inspection in industrial production and to improve the development efficiency and reliability of such systems, this paper designs and implements a general machine vision software framework. This framework is easy to adapt to different hardware devices for secondary development, reducing the workload in generic functional modules and program architecture design, which allows developers to focus on the design and implementation of image-processing algorithms. Based on the MVP software design principles, the framework abstracts and implements the modules common to machine vision-based product appearance quality inspection systems, such as user management, inspection configuration, task management, image acquisition, database configuration, GUI, multi-threaded architecture, IO communication, etc. Using this framework and adding the secondary development of image-processing algorithms, we successfully apply the framework to the quality inspection of the surface defects of bolts.
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference31 articles.
1. Zhang, X., Zhang, J., Ma, M., Chen, Z., Yue, S., He, T., and Xu, X. (2018). A high precision quality inspection system for steel bars based on machine vision. Sensors, 18. 2. Challenges for software engineering in automation;J. Softw. Eng. Appl.,2014 3. Open source machine vision platform for manufacturing and robotics;IFAC-PapersOnLine,2021 4. Akcay, S., Ameln, D., Vaidya, A., Lakshmanan, B., Ahuja, N., and Genc, U. (2022). Anomalib: A Deep Learning Library for Anomaly Detection. arXiv. 5. Dawkins, M., Sherrill, L., Fieldhouse, K., Hoogs, A., Richards, B., Zhang, D., Prasad, L., Williams, K., Lauffenburger, N., and Wang, G. (2017, January 24–31). An open-source platform for underwater image and video analytics. Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, USA.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|