KUKA Robot for sorting labels using YOLO algorithm and packaging in bottled water production process
Article Sidebar
Main Article Content
Abstract
This paper presents how to apply the image processing technology with the deep learning methods using YOLO V5, which is an object detection algorithm with high accuracy and speed applied for the bottled water production process. For sorting the specific label, KUKA robot is used to sort and pack the 3x3 box packaging. The result of the average process time is of 6.288 minutes at the conveyor speed of 3.54 cm per second. Deep convolutional neural network based on the YOLOv5 algorithm is used for the image recognition model. A set of training data is used 1,333 images for 3 types of classification as perfect, damaged and not have labels. After training for 500 rounds, the model has an average loss of 0.0056 and the precision of 0.9723. The experimental results have found that the success rate of classification at 100% from 60 bottles.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright @2021 Engineering Transactions
Faculty of Engineering and Technology
Mahanakorn University of Technology
References
Charan, Allashyam, Chundu Karthik Chowdary, and Peddagowda Komal, "The Future of Machine Vision in Industries-A systematic review", IOP Conference Series: Materials Science and Engineering, Vol. 1224, No. 1, 2022.
B.Suechoey, N.Kulkana and M.Leelajindakrairerk, “Robot Control for Picking Up Objects using 2D Vision Camera”, SAU JORNAL OF SCIENCE & TECHNOLOGY, Vol.6, No.2, July– December 2020.
B.Tanut, N.Kamsuwan, “A Prototype Development of Marigold Classification by Image Processing”, Science and Technology Nakhon Sawan Rajabhat University Jornal, Vol.11, No.13, January-June 2019.
J.-a.Kim, J.-Y.Sung and S.-h.Park, “Comparison of Faster-RCNN, YOLO, and SSD for Real-Time Vehicle Type Recognition”, IEEE Internation Conference on Consumer Electronics-Asia (ICCE-Asia), pp.1-4, 2020.
P.Punyato and N.Sidahao, “Low-Cost Real-Time People Counting System Object Recognition Embedded Systems Raspberry Pi Tiny YOLO”, Engineering Transactions, Vol.22, No.2, pp.72-78, July-December 2019.
N. S. Punn, S. K. Sonbhadra, S. Agarwal and G. Rai, “Monitoring COVID-19 social distancing with person detection and tracking via fine-tuned YOLOv3 and Deepsort Techniques”, arXiv preprint arXiv:2005.01385, 2020.
Z.Cai and N.Vasconcelos, “Cascade R-CNN: High Quality Object Detection and Instance Segmentation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.43, pp.1483-1498, 2021.