한국산학기술학회논문지 (Journal of the Korea Academia-Industrial cooperation Society)

  • 제22권5호
  • /
  • Pages.7-14
  • /
  • 2021
  • /
  • 1975-4701(pISSN)
  • /
  • 2288-4688(eISSN)
한국산학기술학회 (The Korea Academia-Industrial cooperation Society)
권호 표지
DOI QR코드

DOI QR Code

심층 CNN 기반 구조를 이용한 토마토 작물 병해충 분류 모델

Tomato Crop Diseases Classification Models Using Deep CNN-based Architectures

  • 김삼근 (한경대학교 컴퓨터응용수학부(컴퓨터시스템연구소)) ;
  • 안재근 (한경대학교 컴퓨터응용수학부(컴퓨터시스템연구소))
  • Kim, Sam-Keun (School of Computer Engineering & Applied Mathematics, Hankyong National University) ;
  • Ahn, Jae-Geun (School of Computer Engineering & Applied Mathematics, Hankyong National University)
  • 투고 : 2021.02.01
  • 심사 : 2021.05.07
  • 발행 : 2021.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

토마토 작물은 병해충의 영향을 많이 받기 때문에 이를 예방하지 않으면 농업 경제에 막대한 손실을 초래할 수 있다. 따라서 토마토의 다양한 병해충의 진단을 빠르고 정확하게 진단하는 시스템이 요구된다. 본 논문에서는 ImageNet 데이터 셋 상에서 다양하게 사전 학습된 딥러닝 기반 CNN 모델을 적용하여 토마토의 9가지 병해충 및 정상인 경우의 클래스를 분류하는 시스템을 제안한다. PlantVillage 데이터 셋으로부터 발췌한 토마토 잎의 이미지 셋을 3가지 딥러닝 기반 CNN 구조를 갖는 ResNet, Xception, DenseNet의 입력으로 사용한다. 기본 CNN 모델 위에 톱-레벨 분류기를 추가하여 제안 모델을 구성하였으며, 훈련 데이터 셋에 대해 5-fold 교차검증 기법을 적용하여 학습시켰다. 3가지 제안 모델의 학습은 모두 기본 CNN 모델의 계층을 동결하여 학습시키는 전이 학습과 동결을 해제한 후 학습률을 매우 작은 수로 설정하여 학습시키는 미세 조정 학습 두 단계로 진행하였다. 모델 최적화 알고리즘으로는 SGD, RMSprop, Adam을 적용하였다. 실험 결과는 RMSprop 알고리즘이 적용된 DenseNet CNN 모델이 98.63%의 정확도로 가장 우수한 결과를 보였다.

Tomato crops are highly affected by tomato diseases, and if not prevented, a disease can cause severe losses for the agricultural economy. Therefore, there is a need for a system that quickly and accurately diagnoses various tomato diseases. In this paper, we propose a system that classifies nine diseases as well as healthy tomato plants by applying various pretrained deep learning-based CNN models trained on an ImageNet dataset. The tomato leaf image dataset obtained from PlantVillage is provided as input to ResNet, Xception, and DenseNet, which have deep learning-based CNN architectures. The proposed models were constructed by adding a top-level classifier to the basic CNN model, and they were trained by applying a 5-fold cross-validation strategy. All three of the proposed models were trained in two stages: transfer learning (which freezes the layers of the basic CNN model and then trains only the top-level classifiers), and fine-tuned learning (which sets the learning rate to a very small number and trains after unfreezing basic CNN layers). SGD, RMSprop, and Adam were applied as optimization algorithms. The experimental results show that the DenseNet CNN model to which the RMSprop algorithm was applied output the best results, with 98.63% accuracy.

키워드

참고문헌

  1. Dheeb Al Bashish, Malik Braik and Sulieman Bani-Ahmad, "Detection and classification of leaf diseases using K-means-based segmentation and neural networks based classification," Inform Technol J 10, pp.267-275, 2011. DOI: https://doi.org/10.3923/itj.2011.267.275
  2. Jayme Garcia Arnal Barbedo, "A review on the main challenges in automatic plant disease identification based on visible range images," Biosystems Engineering, Vol. 144, pp. 52-60, 2016. DOI: https://doi.org/10.1016/j.biosystemseng.2016.01.017.
  3. Alireza Khoshroo, Arman Arefi, and Jalal Khodaei, "Detection of Red Tomato on Plants using Image Processing Techniques," Agricultural Communications, 2, pp.9-15, 2014. https://www.researchgate.net/publication/267624601_Detection_of_Red_Tomato_on_Plants_using_Image_Processing_Techniques
  4. David Ireri, Eisa Belal, Cedric Okinda, Nelson Makange, and Changying Ji, "A computer vision system for defect discrimination and grading in tomatoes using machine learning and image processing," Artificial Intelligence in Agriculture, Volume 2, pp.28-37, 2019. DOI: https://doi.org/10.1016/j.aiia.2019.06.001
  5. B. Luna-Benoso, J. C. Martinez-Perales, and J. Cortes-Galicia, "Tomato disease detection by means of pattern recognition," International Journal of Computing and Optimization, Vol. 7, no. 1, pp.35-45, 2020. DOI: https://doi.org/10.12988/ijco.2020.9823
  6. Dong Pixia, Wang Xiangdong, "Recognition of Greenhouse Cucumber Disease Based on Image Processing Technology," Open Journal of Applied Sciences, 3, pp.27-31, 2013. DOI: https://doi.org/10.4236/ojapps.2013.31B006
  7. Tejal Deshpande, Sharmila Sengupta and K.S.Raghuvanshi, "Grading and Identification of Disease in Pomegranate Leaf and Fruit", (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 5 (3), pp. 4638-4645, 2014. http://www.ijcsit.com/docs/Volume%205/vol5issue03/ijcsit20140503429.pdf
  8. Khairnar K, Dagade R, "Disease detection and diagnosis on plant using image processing-a review," Int J Comput Appl 108(13), pp. 36-39, 2014. DOI: https://doi.org/10.5120/18973-0445
  9. Arpan Singh Rajput, Shailja Shukla, and S. S. Thakur, "Soybean Leaf Diseases Detection and Classification Using Recent Image Processing Techniques," International Journal of Students' Research in Technology & Management eISSN: 2321-2543, Vol 8, No 3, pp 01-08, 2020. DOI: https://doi.org/10.18510/ijsrtm.2020.831
  10. Bin Liu, Yun Zhang, DongJian He, and Yuxiang Li, "Identification of apple leaf diseases based on deep convolutional neural networks," Symmetry, 10, 2018. DOI: https://doi.org/10.3390/sym10010011
  11. Mohammed Brahimi, Boukhalfa Kamel, and Abdelouahab Moussaoui, "Deep Learning for Tomato Diseases: Classification and Symptoms Visualization," Applied Artificial Intelligence 31(4), pp. 299-315, 2017. DOI:: http://dx.doi.org/10.1080/08839514.2017.1315516
  12. Sharada P. Mohanty, David P. Hughes, and Marcel Salathe, "Using Deep Learning for Image-Based Plant Disease Detection," Frontiers in Plant Science, vol. 7, pp.1-10, 2016. DOI: https://doi.org/10.3389/fpls.2016.01419
  13. Jose A. Jimenez-Berni, Amanda Ramcharan, and Jayme G. Barbedo, "Convolutional Neural Networks for the Automatic Identification of Plant Diseases," Frontiers in Plant Science, vol. 10: 941, 2019. DOI: https://doi.org/10.3389/fpls.2019.00941
  14. Aravind Krishnaswamy Rangarajan, Raja Purushothaman, and Aniirudh Ramesh, "Tomato crop disease classification using pre-trained deep learning algorithm," Procedia Computer Science, Volume 133, pp. 1040-1047, 2018. DOI: https://doi.org/10.1016/j.procs.2018.07.070.
  15. Jiten Khurana, Anurag Sharma, Harshit Singh Chhabra, and Rahul Nijhawan, "An Integrated Deep Learning Framework of Tomato Leaf Disease Detection," International Journal of Innovative Technology and Exploring Engineering (IJITEE), Volume-8, Issue-11S, 2019. Available at: https://www.ijitee.org/wp-content/uploads/papers/v8i11S/K101009811S19.pdf
  16. H. Hong, J. Lin and F. Huang, "Tomato Disease Detection and Classification by Deep Learning," 2020 International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Fuzhou, China, pp. 25-29, 2020. DOI: https://doi.org/10.1109/ICBAIE49996.2020.00012
  17. PlantVillage Dataset, https://www.kaggle.com/emmarex/plantdisease
  18. Olga Russakovsky*, Jia Deng*, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei (* = equal contribution), "ImageNet Large Scale Visual Recognition Challenge", International Journal of Computer Vision(IJCV), Vol 115, Issue 3, pp. 211-252, 2015. http://www.image-net.org/challenges/LSVRC/ https://doi.org/10.1007/s11263-015-0816-y
  19. ImageNet. http://www.image-net.org
  20. Arthur Flexer, "Statistical evaluation of neural networks experiments: Minimum requirements and current practice", In Proceedings of the 13th European Meeting on Cybernetics and Systems Research, volume 2, pp.1005-1008, Vienna, Austria, 1996. https://researchgate.net/publication/2627930_Statistical_Evaluation_of_Neural_Network_Experiments_Minimum_Requirements_and_Current_Practice.