STUDY OF IMPURITIES DETECTION IN FROZEN SPINACH WITH YOLOV4 DEEP LEARNING MODEL
DOI:
https://doi.org/10.14456/tisr.2023.12Keywords:
Deep Learning, Detection, Classification, Frozen Spinach, ImpurityAbstract
Currently, a technology exists that detects impurities in frozen food products. It helps in keeping control of the food safety and quality. The YOLO deep learning model is used combined with a high-resolution camera to develop a real-time impurity detection system for frozen food. It has the ability to locate and detect small objects. Therefore, the objective of this research is to increase food impurity detection. Therefore, the objective of this research is to increase food impurity detection. A data set containing images of plastic, glass, string, glass, wood, and frozen spinach was generated. A YOLOv4 model was trained on the image dataset. The model performance can be tested and evaluated using a multiclass confusion matrix. Results show that the model has an average loss of 5.55 and a mean Average Precision (mAP) of 76%. The model showed that plastic had the highest detection efficiency when used to detect and classify images of frozen spinach combined with only one impurity, followed by string, glass, rock, and wood, respectively. The accuracy score, precision score, recall, and F1-Score of plastic were 52.22%, 52.94%, 55.38%, and 54.14%, respectively.
References
เตชินท์ วรสิทธิ์, ธีระ ภัทราพรนันท์, ธีรยุทธ ตู้จินดา, วสิน สินธุภิญโญ, กรรณทิพย์ กิรติรัตนพฤกษ์, พิชญกาญจน์ เต็มนิรันรัตน์, อภิชน กิจวิมลรัตน์, จินตนา อันอาตม์งาม และ สุจินต์ ภัทรภูวดล. (2565). การประยุกต์ใช้เทคนิคการเรียนรู้เชิงลึกสำหรับการรู้จำโรคขอบใบแห้งและโรคไหม้ของข้าว. วารสารแก่นเกษตร, 50(1), 216-228.
พุฒิพงศ์ จันทร์แจ่ม. (2563). การปรับปรุงประสิทธิภาพของกระบวนการบริการลูกค้าโดยใช้การวิเคราะห์จากกล้องวงจรปิด. การค้นคว้าอิสระ วิทยาศาสตรมหาบัณฑิต, สถาบันบัณฑิตพัฒนบริหารศาสตร์.
Bochkovskiy, A., Wang, C., & Liao, H. (2020). Yolov4: Optimal Speed and Accuracy of Object Detection. Retrieved from https://arxiv.org/pdf/2004.10934.pdf?fbclid=IwAR0TyLXaKDLIrotdQX5Pd_nRJPGESQNOzj--RG1ob5aS8GdLRWCFm37ylo4.
Dermesonluoglu, E., Katsaros, G., Tsevdou, M., Giannakourou, M., & Taoukis, P. (2015). Kinetic Study of Quality Indices and Shelf Life Modelling of Frozen Spinach Under Dynamic Conditions of the Cold Chain. Journal of Food Engineering, 148, 13-23.
Luque, A., Carrasco, A., Martín, A., & Heras, A. (2019). The Impact of Class Imbalance in Classification Performance Metrics Based on the Binary Confusion Matrix. Pattern Recognition, 91, 216-231.
Rong, D., Xie, L., & Ying, Y. (2019). Computer Vision Detection of Foreign Objects in Walnuts Using Deep Learning. Computers and Electronics in Agriculture, 162, 1001-1010.
Solawetz, J. (2020). What are Anchor Boxes in Object Detection?. Retrieved from https://blog.roboflow.com/what-is-an-anchor-box/.
Swiezewski, J. (2020). YOLO Algorithm and YOLO Object Detection. Retrieved from https://appsilon.com/object-detection-yolo-algorithm/.
The Observatory of Economic Complexity. (2021). Spinach, Frozen, Uncook Steamed or Boiled. Retrieved from https://oec.world/en/visualize/tree_map/hs92/export/show/all/2071030/2021/.
Wu, D., Lv, S., Jiang, M., & Song, H. (2020). Using Channel Pruning-Based YOLOv4 Deep Learning Algorithm for the Real-Time and Accurate Detection of Apple Flowers in Natural Environments. Computers and Electronics in Agriculture, 178, 105742.
Zhu, L., & Spachos, P. (2020). Food Grading System using Support Vector Machine and YOLOv3 Methods. A paper presented at the 2020 IEEE Symposium on Computers and Communications, Rennes, France.
Zhu, L., Spachos, P., Pensini, E., & Plataniotis, K. (2021). Deep Learning and Machine Vision for Food Processing: A Survey. Current Research in Food Science, 4, 233-249.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Authors
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
.png)
