Decorative Wreaths Assessment Using a Deep Learning Approach
DOI:
https://doi.org/10.69681/lajae.v6i1.31Keywords:
Floriculture, YOLO, Deep learning, Accuracy, Precision, Recall, MaPAbstract
The floriculture industry is an increasing sector in Baja California, that exports most of its production. Products like decorative wreaths depend mainly on human inspection, which has often been prone to human errors and challenges in meeting the quality criteria. Implementing advanced technologies and automated inspection methods in floriculture, aiming to eradicate human errors, seems to contribute to minimizing defective products and ensuring compliance with quality standards and export regulations. In this paper, we assess the YOLO implementation, a deep learning approach, in the defect identification process. Results show that accuracy ranges from 48.4% to 81.3% and MaP from 53.2% to 87.6% using ten epochs. This paper provides valuable evidence for future studies and implementations regarding deep learning approaches used to evaluate the visual characteristics in the floriculture industry.
Downloads
References
Gobierno de Mexico, “Las flores están en el campo, en las miradas, en las palabras...”, Accessed: Jun. 26, 2023. [Online]. Available: https://www.gob.mx/agricultura/articulos/las-flores-estan-en-el-campo-en-las-miradas-en-las-palabras#:~:text=La%20floricultura%20mexicana%20es%20una,producci%C3%B3n%20la%20realizan%20manos%20femeninas.
Gobierno de Mexico, “Floricultura, cultivando belleza y ganancias”, Accessed: Jun. 26, 2023. [Online]. Available: https://www.gob.mx/agricultura/es/articulos/floricultura-cultivando-belleza-y-ganancias
J. Jesús Ramírez Hernández and J. A. Avitia-Rodríguez, “MEXICAN FLORICULTURE IN THE 21ST CENTURY: ITS PERFORMANCE IN INTERNATIONAL MARKETS.”
S. Jamal and J. E. Judith, “Review on Automated Leaf Disease Prediction Systems,” in Proceedings of the ACCTHPA 2023 - Conference on Advanced Computing and Communication Technologies for High Performance Applications, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ACCTHPA57160.2023.10083382.
S. Sundaram and A. Zeid, “Artificial Intelligence-Based Smart Quality Inspection for Manufacturing,” Micromachines (Basel), vol. 14, no. 3, p. 570, Feb. 2023, doi: 10.3390/mi14030570.
J. E. See, “SANDIA REPORT Visual Inspection: A Review of the Literature,” 2012. [Online]. Available: http://www.ntis.gov/help/ordermethods.asp?loc=7-4-0#online
G. Oil and G. Digital, “The Impact of Digital on Unplanned Downtime AN OFFSHORE OIL AND GAS PERSPECTIVE EXECUTIVE SUMMARY ‘DIGITIZATION ENABLES OFFSHORE OPERATORS TO REDUCE UNPLANNED DOWNTIME WHILE SIMULTANEOUSLY REDUCING RISKS.,’” 2016.
J. E. See, “The Role of Visual Inspection in the 21 st Century.”
M. Babic, M. A. Farahani, and T. Wuest, “Image Based Quality Inspection in Smart Manufacturing Systems: A Literature Review,” in Procedia CIRP, Elsevier B.V., 2021, pp. 262–267. doi: 10.1016/j.procir.2021.10.042.
A. Cruz et al., “Detection of grapevine yellows symptoms in Vitis vinifera L. with artificial intelligence,” Comput Electron Agric, vol. 157, pp. 63–76, Feb. 2019, doi: 10.1016/j.compag.2018.12.028.
S. Veeragandham and H. Santhi, “Effectiveness of convolutional layers in pre-trained models for classifying common weeds in groundnut and corn crops,” Computers and Electrical Engineering, vol. 103, Oct. 2022, doi: 10.1016/j.compeleceng.2022.108315.
R. Zhu, H. Zou, Z. Li, and R. Ni, “Apple-Net: A Model Based on Improved YOLOv5 to Detect the Apple Leaf Diseases,” Plants, vol. 12, no. 1, Jan. 2023, doi: 10.3390/plants12010169.
S. Tan et al., “Machine Learning Approaches for Rice Seedling Growth Stages Detection,” Front Plant Sci, vol. 13, Jun. 2022, doi: 10.3389/fpls.2022.914771.
N. Ismail and O. A. Malik, “Real-time Visual Inspection System for Grading Fruits using Computer Vision and Deep Learning Techniques,” Information Processing in Agriculture, 2021, doi: 10.1016/j.inpa.2021.01.005.
V. Gonzalez-Huitron, J. A. León-Borges, A. E. Rodriguez-Mata, L. E. Amabilis-Sosa, B. Ramírez-Pereda, and H. Rodriguez, “Disease detection in tomato leaves via CNN with lightweight architectures implemented in Raspberry Pi 4,” Comput Electron Agric, vol. 181, Feb. 2021, doi: 10.1016/j.compag.2020.105951.
P. T. Q. Anh, D. Q. Thuyet, and Y. Kobayashi, “Image classification of root-trimmed garlic using multi-label and multi-class classification with deep convolutional neural network,” Postharvest Biol Technol, vol. 190, Aug. 2022, doi: 10.1016/j.postharvbio.2022.111956.
A. Nasiri, A. Taheri-Garavand, and Y. D. Zhang, “Image-based deep learning automated sorting of date fruit,” Postharvest Biol Technol, vol. 153, pp. 133–141, Jul. 2019, doi: 10.1016/j.postharvbio.2019.04.003.
H. Li, C. Li, G. Li, and L. Chen, “A real-time table grape detection method based on improved YOLOv4-tiny network in complex background,” Biosyst Eng, vol. 212, pp. 347–359, Dec. 2021, doi: 10.1016/j.biosystemseng.2021.11.011.
Y. Ge et al., “Tracking and Counting of Tomato at Different Growth Period Using an Improving YOLO-Deepsort Network for Inspection Robot,” Machines, vol. 10, no. 6, Jun. 2022, doi: 10.3390/machines10060489.
P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros, “Image-to-Image Translation with Conditional Adversarial Networks,” Nov. 2016, [Online]. Available: http://arxiv.org/abs/1611.07004
Downloads
Published
How to Cite
License
Copyright (c) 2024 Latin American Journal of Applied Engineeringg
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with Latin American Journal of Applied Engineering agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License 4.0 that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
