Real-Time Deep Learning based Tomato Fruit Quality Control in Conveyor Belt
Abstract views: 394
/ 
PDF downloads: 373
DOI:
https://doi.org/10.59287/ijanser.352Keywords:
Deep Learning, Quality Control, Tomato, Real Time, Object DetectionAbstract
Quality control is crucial in ensuring that the finished goods adhere to the specified requirements and standards in a manufacturing or production context. One key area where quality control is essential for sorting and separating goods on a conveyor belt. Automating this process can significantly improve the efficiency and accuracy of quality control. Manual quality control is a labor-intensive and time-consuming process that can lead to human error and inconsistencies. On the other hand, automation allows for the use of technology, such as machine vision and artificial intelligence, to quickly and accurately sort and separate goods based on predefined criteria. Automation also enables real-time monitoring and data collection, which can provide valuable insights into the manufacturing process and help identify areas for improvement.
Additionally, automation can improve the speed and efficiency of the sorting process, allowing for greater throughput of goods and increasing productivity. Furthermore, automation can reduce workplace injuries, as manual sorting and separation can be physically demanding and lead to repetitive strain injuries. In summary, automating quality control in the sorting and separating of goods on a conveyor belt is essential for improving the accuracy and efficiency of the process, reducing the risk of human error and workplace injuries, and providing valuable insights into the manufacturing process.
This paper used real-time deep learning-based tomato fruit quality control in conveyor belts with IP cameras. User interface and object detection models were used. For an automated separation procedure, tomato form, quality, size, and other variables were assessed in real-time. YoloV4 tiny, SSDMobileNet, and Faster RCNN models were utilized, and real-time accuracy of 88, 87, and 92 percent was attained. We carried out hyperparameter optimization, fine-tuning, and data augmentation.
Downloads
References
Pogonyi, A., Pék, Z., Helyes, L., & Lugasi, A. (2005). Effect of grafting on the tomato's yield, quality, and main fruit components in spring force. Acta Alimentaria, 34(4), 453-462.
A. Mohapatra, S. Shanmugasundaram, and R. Malmathanraj, ‘‘Grading of ripening stages of red banana using dielectric properties changes and image processing approach,’’ Comput. Electron. Agricult., vol. 143, no. 382,
pp. 100–110, 2017.
De Luna, R. G., Dadios, E. P., Bandala, A. A., & Vicerra, R. R. P. (2019). Tomato fruit image dataset for deep transfer learning-based defect detection. In 2019 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation, and Mechatronics (RAM) (pp. 356-361). IEEE.
Sanaeifar, A., ZakiDizaji, H., Jafari, A., & de la Guardia, M. (2017). Early detection of contamination and defect in foodstuffs by electronic nose: A review. TrAC Trends in Analytical Chemistry, 97, 257- 271.
da Costa, A. Z., Figueroa, H. E., & Fracarolli, J. A. (2020). Computer vision based detection of external defects on tomatoes using deep learning. Biosystems Engineering, 190, 131-144.
Zhang, B., Huang, W., Li, J., Zhao, C., Fan, S., Wu, J., & Liu, C. (2014). A review of the principles, developments and applications of computer vision for external quality inspection of fruits and vegetables. Food Research International, 62, 326-343.
Blasco, J., Aleixos, N., Molto, E., 2007. Computer vision detection of peel defects in citrus by
means of a region oriented segmentation algorithm. J. Food Eng. 81 (3), 535–543.
H. Lu, F. Wang, X. Liu, and Y. Wu, ‘‘Rapid assessment of tomato ripeness using visible/near-infrared spectroscopy and machine vision,’’ Food Anal. Methods, vol. 10, no. 6, pp. 1721–1726, 2017.
S. Bargoti and J. Underwood, ‘‘Deep fruit detection in orchards,’’ in Proc. IEEE Int. Conf. Robot. Autom., May 2017, pp. 3626–3633
Sembiring, A., Budiman, A., & Lestari, Y. D. (2017). Design and control of agricultural robot for tomato plants treatment and harvesting. In Journal of Physics: Conference Series (Vol. 930, No. 1, p. 012019). IOP Publishing.
Oktarina, Y., Dewi, T., Risma, P., & Nawawi, M. (2020). Tomato harvesting arm robot manipulator; a pilot project. In Journal of Physics: Conference Series (Vol. 1500, No. 1, p. 012003). IOP Publishing.
Lili, W., Bo, Z., Jinwei, F., Xiaoan, H., Shu, W., Yashuo, L., ... & Chongfeng, W. (2017). Development of a tomato harvesting robot used in greenhouse. International Journal of Agricultural and Biological Engineering, 10(4), 140-149.
Feng, Q., Zou, W., Fan, P., Zhang, C., & Wang, X. (2018). Design and test of robotic harvesting system for cherry tomato. International Journal of Agricultural and Biological Engineering, 11(1), 96-100.
Jahns, G., Nielsen, H.M., Paul, W., 2001. Measuring image analysis attributes and modelling fuzzy consumer aspects for tomato quality grading. Comput. Electron. Agric.31(1),17–29.https://doi.org/10.1016/S0168-1699(00)00171-X
Moallem, P., Serajoddin, A., Pourghassem, H., 2017. Computer vision-based apple grading for golden delicious apples based on surface features. Inf. Process. Agric. 4 (1), 33–40.
[16] Moltó, E., Blasco, J., Gómez-Sanchís, J., 2010. Analysis of hyperspectral images of citrus fruits. Hyperspectral Imaging for Food Quality Analysis and Control. Elsevier, pp. 321–348
