DOI QR코드

DOI QR Code

Integrated Deep Learning Models for Precise Disease Diagnosis in Pepper Crops: Performance Analysis of YOLOv8, ResNet50, and Faster R-CNN

고추 작물의 정밀 질병 진단을 위한 딥러닝 모델 통합 연구: YOLOv8, ResNet50, Faster R-CNN의 성능 분석

  • 서지인 (순천대학교 스마트농업전공) ;
  • 심현 (국립순천대학교 스마트농업전공학과)
  • Received : 2024.06.30
  • Accepted : 2024.07.25
  • Published : 2024.08.31

Abstract

The purpose of this study is to diagnose diseases in pepper crops using YOLOv8, ResNet50, and Faster R-CNN models and compare their performance. The first model utilizes YOLOv8 for disease diagnosis, the second model uses ResNet50 alone, the third model combines YOLOv8 and ResNet50, and the fourth model uses Faster R-CNN. The performance of each model was evaluated using metrics such as accuracy, precision, recall, and F1-Score. The results show that the combined YOLOv8 and ResNet50 model achieved the highest performance, while the YOLOv8 standalone model also demonstrated high performance.

본 연구의 목적은 YOLOv8, ResNet50, Faster R-CNN 모델을 활용하여 고추 작물의 질병을 진단하고, 각 모델의 성능을 비교하는 것이다. 첫 번째 모델은 YOLOv8을 사용하여 질병을 진단하였고, 두 번째 모델은 ResNet50을 단독으로 사용하였다. 세 번째 모델은 YOLOv8과 ResNet50을 결합하여 질병을 진단하였으며, 네 번째 모델은 Faster R-CNN을 사용하여 질병을 진단하였다. 각 모델의 성능은 정확도, 정밀도, 재현율, F1-Score 지표로 평가된다. 연구 결과, YOLOv8과 ResNet50을 결합한 모델이 가장 높은 성능을 보였으며, YOLOv8 단독 모델도 높은 성능을 나타냈다.

Keywords

Acknowledgement

본 논문은 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 지역지능화혁신인재양성사업임(IITP-2024-2020-0-01489).

References

  1. B. Richard, A. Qi, and B. D. L. Fitt, "Control of crop diseases through Integrated Crop Managementto deliver climate-smart farming systems for low- and high-input crop production," Plant Pathology, vol. 71, no. 1, 2022, pp. 187-206. 
  2. S. Aggarwal, M. Suchithra, N. Chandramouli, M. Sarada, A. Verma, D. Vetrithangam, B. Pant, and B. A. Adugna, "Rice Disease Detection Using Artificial Intelligence and MachineLearning Techniques to Improvise Agro-Business," Scientific Programming, vol. 2022, no. 1, 2022. 
  3. Y. Koo, "Analysis on Big data, IoT, Artificial intelligence using Keyword Network," Journal of the Korea Institute of Electronic Communication Sciences, vol. 15, no. 6, Dec. 2020, pp. 1137-1144. 
  4. L. Jun and W. Xuewei, "Tomato Diseases and Pests Detection Based on Improved Yolo V3 Convolutional Neural Network," Frontiers in Plant Science, vol. 11, article 898, June 2020, pp. 898. http://dx.doi: 10.3389/fpls.2020.00898
  5. G. Liu, J. C. Nouaze, P. L. Touko Mbouembe, and J. Kim, "YOLO-Tomato: A Robust Algorithm for Tomato Detection Based on YOLOv3", Sensors, vol. 20, no. 7, Apr. 2020. 
  6. H. Sim, S. Choi, and H. Kim, "Algorithm Improvement Through AI-Based Casting Process Parameter Optimization," Journal of the Korea Institute of Electronic Communication Sciences, vol. 18, no. 3, June 2023, pp. 441-448. http://dx.doi.org/10.13067/JKIECS.2023.18.3.441 
  7. H. Sim and H. Kim, "Development of AI-based Smart Agriculture Early Warning System," Journal of the Korea Society of Computer and Information, vol. 28, no. 12, Dec. 2023, pp. 67-77. 
  8. A. J, J. Eunice, D. E. Popescu, M. K. Chowdary and J. Hemanth, "Deep Learning-Based Leaf Disease Detection in Crops Using Images for Agricultural Applications," Agronomy, vol. 12, no. 10, 2022. 
  9. B. Tugrul, E. Elfatimi, and R. Eryigit, "Convolutional Neural Networks in Detection of Plant Leaf Diseases: A Review," Agriculture, vol. 12, no. 8, Aug. 2022. 
  10. X. Gong and S. Zhang, "A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNN," Agriculture, vol. 13, no. 2, 2023. 
  11. S. Jeon, S. Kwon, H. Yi, J. Lee, and J. Bae, "Research on Pepper Anthrax Detection Using YOLOv8 Segmentation Model," Proceedings of Korean Insitute of Information Technology Conference, Jeju City, Korea, 2023, pp. 577-580. 
  12. S. Lee, S. Lin, and S. Chen, "Identification of tea foliar diseases and pest damage under practical field conditions using a convolutional neural network," Plant Pathol, vol. 69, no. 9, 2020, pp. 1601-1812.