AUTOMATION OF FUNCTIONAL CONTROL OF PRESSURE SENSOR DISPLAY MODULES USING MACHINE VISION SYSTEMS
https://doi.org/10.26583/vestnik.2024.5.8
EDN: VPCWIG
Abstract
The article considers the application of various machine vision algorithms for automation of functional testing of LCD displays of pressure sensors. Neural networks and classical algorithms, as well as the algorithm developed by the author, are analyzed. The purpose of the study is to find an algorithm that can be used in the development of an automatic display testing system. The algorithm should be highly accurate and minimize the number of false negative results in order to avoid missing defective products. It should also be able to detect backlight defects, lack of segment glow, unexpected segment glow, spots and mechanical damage on the display. The article describes the stages of algorithm development, including image preprocessing, binarization, analysis and defect search. The presented results of testing the algorithm on a test sample confirm its high accuracy and completeness. In the course of the work, it was found that no standard algorithm is suitable for the functional testing of display modules, while the algorithm developed by the author fully meets all the requirements. The developed algorithm is used to create an automatic LCD display testing system, currently used in the production of pressure sensors.
References
1. David E.E., Selfridge O.G. 1962. Eyes and Ears for Computers. Proceedings of the IRE, 50, 1093-1101. https://doi.org/10.1109/JRPROC.1962.288011.
2. Theodore L. Warren, Kenneth R. Whelan, Ar-nold G. Reinhold. Vision system (Patent No. US4577344A). United States, 1983. Assignee: Acuity Imaging.
3. Emelyanov S.G. Metody` i sredstva obrabotki izobrazhenij [Methods and means of image processing]. Priborostroenie, 2009. Vol. 52, No. 2. Pp. 11–12 (in Russian).
4. Vinokurov I.V. Using a convolutional neural network to recognize text elements in poor quality scanned images. Program systems: theory and applications. 2022. Vol. 13, no. 3 (54). Pp. 45–59.
5. Rokunuzzaman, Jayasuriya, H.P. Development of a low cost machine vision system for sorting of tomatoes. Agricultural Engineering International: The CIGR Journal, 2013. Vol. 15. Pp. 173–180.
6. Tsareva E. Mashinnoe zrenie dlya kontrolya kachestva upakovki vypuskaemoj produkcii [Machine vision for quality control of product packaging]. Tara i upakovka, 2019. No. 2. Рр. 10–12 (in Russian). Available at: https://www.mallenom.ru/Docs/Machine_vision_ article_may2019.pdf (accessed: 19.04.2024).
7. Rakov N.S., Palmov S.V. Mashinnoe zrenie [Machine vision] // Forum molody`x ucheny`x [Forum of young scientists]. 2018. No. 4 (20). Available at: https://cyberleninka.ru/article/n/ mashinnoe-zrenie (accessed: 19.04.2024).
8. Goodfellow Y., Bengio I. Glubokoe obuchenie [Deep learning]. Moscow, DMK Press Publ., 2018. 652 p.
9. Muller A. Vvedenie v mashinnoe obuchenie s pomoshch'yu Python [Introduction to Machine Learning with Python]. Moscow, Gevissta Publ., 2017.
10. Ferguson Max K., Ronay A., Lee Y-T.T, Law K.H. Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning. Smart Sustain. Manuf. Syst., 2018, Vol. 2(1), Pp. 137–164. http://doi.org/10.1520/SSMS20180033
Review
For citations:
Dneprovskii I.V. AUTOMATION OF FUNCTIONAL CONTROL OF PRESSURE SENSOR DISPLAY MODULES USING MACHINE VISION SYSTEMS. Vestnik natsional'nogo issledovatel'skogo yadernogo universiteta "MIFI". 2024;13(5):358-370. (In Russ.) https://doi.org/10.26583/vestnik.2024.5.8. EDN: VPCWIG
Views:
112
Email this article 