Journal of Bio-Environment Control (생물환경조절학회지)

The Korean Society for Bio-Environment Control (한국생물환경조절학회)
권호 표지
DOI QR코드

DOI QR Code

Tea Leaf Disease Classification Using Artificial Intelligence (AI) Models

인공지능(AI) 모델을 사용한 차나무 잎의 병해 분류

  • K.P.S. Kumaratenna (Department of Horticultural Science, Jeju National University) ;
  • Young-Yeol Cho (Department of Horticultural Science, Jeju National University)
  • 피우미 사우미야 쿠마라테나 (제주대학교 생명자원과학대학 원예학과) ;
  • 조영열 (제주대학교 생명자원과학대학 원예학과)
  • Received : 2023.09.15
  • Accepted : 2023.11.20
  • Published : 2024.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, five artificial intelligence (AI) models: Inception v3, SqueezeNet (local), VGG-16, Painters, and DeepLoc were used to classify tea leaf diseases. Eight image categories were used: healthy, algal leaf spot, anthracnose, bird's eye spot, brown blight, gray blight, red leaf spot, and white spot. Software used in this study was Orange 3 which functions as a Python library for visual programming, that operates through an interface that generates workflows to visually manipulate and analyze the data. The precision of each AI model was recorded to select the ideal AI model. All models were trained using the Adam solver, rectified linear unit activation function, 100 neurons in the hidden layers, 200 maximum number of iterations in the neural network, and 0.0001 regularizations. To extend the functionality of Orange 3, new add-ons can be installed and, this study image analytics add-on was newly added which is required for image analysis. For the training model, the import image, image embedding, neural network, test and score, and confusion matrix widgets were used, whereas the import images, image embedding, predictions, and image viewer widgets were used for the prediction. Precisions of the neural networks of the five AI models (Inception v3, SqueezeNet (local), VGG-16, Painters, and DeepLoc) were 0.807, 0.901, 0.780, 0.800, and 0.771, respectively. Finally, the SqueezeNet (local) model was selected as the optimal AI model for the detection of tea diseases using tea leaf images owing to its high precision and good performance throughout the confusion matrix.

이 연구에서는 Inception V3, SqueezeNet(local), VGG-16, Painters 및 DeepLoc의 다섯 가지 인공지능(AI) 모델을 사용하여 차나무 잎의 병해를 분류하였다. 여덟 가지 이미지 카테고리를 사용하였는데, healthy, algal leaf spot, anthracnose, bird's eye spot, brown blight, gray blight, red leaf spot, and white spot였다. 이 연구에서 사용한 소프트웨어는 데이터 시각적 프로그래밍을 위한 파이썬 라이브러리로 작동하는 Orange3였다. 이는 데이터를 시각적으로 조작하여 분석하기 위한 워크플로를 생성하는 인터페이스를 통해 작동되었다. 각 AI 모델의 정확도로 최적의 AI 모델을 선택하였다. 모든 모델은 Adam 최적화, ReLU 활성화 함수, 은닉 레이어에 100개의 뉴런, 신경망의 최대 반복 횟수가 200회, 그리고 0.0001 정규화를 사용하여 훈련되었다. Orange3 기능을 확장하기 위해 새로운 이미지 분석 Add-on을 설치하였다. 훈련 모델에서는 이미지 가져오기(import image), 이미지 임베딩(image embedding), 신경망(neural network), 테스트 및 점수(test and score), 혼동 행렬(confusion matrix) 위젯이 사용되었으며, 예측에는 이미지 가져오기(import image), 이미지 임베딩(image embedding), 예측(prediction) 및 이미지 뷰어(image viewer) 위젯이 사용되었다. 다섯 AI 모델[Inception V3, SqueezeNet(로컬), VGG-16, Painters 및 DeepLoc]의 신경망 정밀도는 각각 0.807, 0.901, 0.780, 0.800 및 0.771이었다. 결론적으로 SqueezeNet(local) 모델이 차나무 잎 이미지를 사용하여 차병해 탐색을 위한 최적 AI 모델로 선택되었으며, 정확도와 혼동 행렬을 통해 뛰어난 성능을 보였다.

Keywords

Acknowledgement

This work was supported by Korea Institute of Planning and Evaluation for Technology in Food, Agriculture and Forestry (IPET) and Korea Smart Fam R&D Foundation (KosFarm) through Smart Farm Innovation Technology Development Progarm, funded by Ministry of Agriculture, Food and Rural Affairs (MAFRA) and Ministry of Science and ICT (MSIT), Rural Development Administration (RDA) (421009043HD020).

References

  1. Barbedo J.G.A. 2016, A review on the main challenges in automatic plant disease identification based on visible range ima ges. Biosyst Eng 144:52-60. doi:10.1016/j.biosystemseng.2016.01.017
  2. Chakruno P., S. Banik, and K. Sumi 2022, Important diseases of tea (Camellia sinensis L.) and their integrated management. In Diseases of Horticultural Crops: Diagnosis and Management, vol 4. Apple Academic Press, USA, pp 119-138. doi:10.1201/9781003160472-7
  3. Chugh G., A. Sharma, P. Choudhary, and R. Khanna 2020, Potato leaf disease detection using InceptionV3. Int Res J Eng Technol 7:1363-1366.
  4. Datta S., and N. Gupta 2023, A novel approach for the detection of tea leaf disease using deep neural network. Procedia Comput Sci 218:2273-2286. doi:10.1016/j.procs.2023.01.203
  5. Demsar J., and B. Zupan 2012, Orange data mining fruitful and fun. Inf Druzba IS 6:1-486.
  6. Demsar J., T. Curk, A. Erjavec, C. Gorup, T. Hocevar, M. Milutinovic, M. Mozina, M. Polajnar, M. Toplak, and A. Staric, et al. 2013, Orange data mining toolbox in Python. J Mach Learn Res 14:2349-2353.
  7. Guo T., J. Dong, H. Li, and Y. Gao 2017, Simple convolutional neural network on image classification. In IEEE 2017 2nd International Conference on Big Data Analysis (ICBDA), pp 721-724. doi:10.1109/ICBDA.2017.8078730
  8. Hidayatuloh A., M. Nursalman, and E. Nugraha 2018, Identification of tomato plant diseases by leaf image using Squeezenet model. In 2018 International Conference on Information Technology Systems and Innovation (ICITSI), pp 199-204. doi:10.1109/ICITSI.2018.8696087
  9. Hu G., X. Yang, Y. Zhang, and M. Wan 2019, Identification of tea leaf diseases by using an improved deep convolutional neural network. Sustain Comput Inform Syst 24:100353. doi:10.1016/j.suscom.2019.100353
  10. Ishak A., K. Siregar, R. Ginting, and M. Afif 2020, Orange software usage in data mining classification method on the dataset lenses. In IOP Conference Series: Materials Science and Engineering (IOP Publishing) 1003(1):012113. doi:10.1088/1757-899X/1003/1/012113
  11. Jiang X., Y. Pang, X. Li, J. Pan, and Y. Xie 2018, Deep neural networks with elastic rectified linear units for object recognition. Neurocomputing 275:1132-1139. doi:10.1016/j.neucom.2017.09.056
  12. Kaggle Data Science Company 2017, https://www.kaggle.com/ Accessed 03 May 2023.
  13. Kansara D., and V. Sawant 2020, Comparison of traditional machine learning and deep learning approaches for sentiment analysis. In Advanced Computing Technologies and Applications: Proceedings of 2nd International Conference on Advanced Computing Technologies and Applications-ICACTA Springer, Singapore, pp 365-377.
  14. Keith L., W.H. Ko, and D.M. Sato 2006, Identification guide for diseases of tea (Camellia sinensis): Plant Disease PD-33. University of Hawaii, Honolulu, HI, USA.
  15. Khan E., M.Z.U. Rehman, F. Ahmed, and M.A. Khan 2021, Classification of diseases in citrus fruits using SqueezeNet. In IEEE 2021 International Conference on Applied and Engineering Mathematics (ICAEM), pp 67-72. doi:10.1109/ICAEM53552.2021.9547133
  16. Kimutai G., and A. Forster 2022, Tea sickness dataset. Mendeley Data V2. doi:10.17632/j32xdt2ff5.2
  17. Latha R.S., G.R. Sreekanth, R.C. Suganthe, R. Rajadevi, S. Karthikeyan, S. Kanivel, and B. Inbaraj 2021, Automatic detection of tea leaf diseases using deep convolution neural network. In 2021 International Conference on Computer Communication and Informatics (ICCCI), pp 1-6. doi:10.1109/ICCCI50826.2021.9402225
  18. Mahesh B. 2020, Machine learning algorithms-a review. Int J Sci Res 9:381-386. doi:10.21275/ART20203995
  19. Mikolajczyk A., and M. Grochowski 2018, Data augmentation for improving deep learning in image classification problem. In 2018 International Interdisciplinary PhD Workshop (IIPhDW), pp 117-122.
  20. Mirza A.H. 2018, Computer network intrusion detection using various classifiers and ensemble learning. In 2018 26th Signal Processing and Communications Applications Conference (SIU), pp 1-4. doi:10.1109/SIU.2018.8404704
  21. Mohapatra S., and T. Swarnkar 2021, Comparative study of different orange data mining tool-based AI techniques in image classification. In S Das, MN Mohanty, eds, Advances in Intelligent Computing and Communication: Lecture Notes in Networks and Systems, vol 202. Springer, Singapore, pp 611-620. doi:10.1007/978-981-16-0695-3_57
  22. Nanehkaran Y.A., D. Zhang, J. Chen, Y. Tian, and N. Al-Nabhan 2020, Recognition of plant leaf diseases based on computer vision. J Ambient Intell Human Comput pp 1-18. doi:10.1007/s12652-020-02505-x
  23. Neyshabur B., S. Bhojanapalli, D. McAllester, and N. Srebro 2017, Exploring generalization in deep learning. Adv Neural Inf Process Syst 30.
  24. Nusrat I., and S.B. Jang 2018, A comparison of regularization techniques in deep neural networks. Symmetry 10(11):648. doi:10.3390/sym10110648
  25. Patro V.M., and M.R. Patra 2014, Augmenting weighted average with confusion matrix to enhance classification accuracy. Trans Mach Learn Artif Intell 2(4):77-91. doi:10.14738/tmlai.24.328
  26. Ratra R., and P. Gulia 2020, Experimental evaluation of open source data mining tools (WEKA and Orange). Int J Eng Trends Technol 68(8):30-35. doi:10.14445/22315381/IJETTV68I8P206S
  27. Raut P., and A. Dani 2020, Correlation between number of hidden layers and accuracy of artificial neural network. In Advanced Computing Technologies and Applications: Proceedings of 2nd International Conference on Advanced Computing Technologies and Applications-ICACTA. Springer, Singapore, pp 513-521. doi:10.1007/978-981-15-3242-9_49
  28. Shafi I., J. Ahmad, S.I. Shah, and F.M. Kashif 2006, Impact of varying neurons and hidden layers in neural network architecture for a time frequency application. In 2006 International Multitopic Conference, pp 188-193. doi:10.1109/INMIC.2006.358160
  29. Sharma S, S. Sharma, and A. Athaiya 2020, Activation functions in neural networks. Int J Eng Appl Sci 4(12):310-316. doi:10.33564/IJEAST.2020.v04i12.054
  30. Shi Y., T. ValizadehAslani, J. Wang, P. Ren, Y. Zhang, M. Hu, and H. Liang 2022, Improving imbalanced learning by pre-finetuning with data augmentation. In Fourth International Workshop on Learning with Imbalanced Domains: Theory and Applications, pp 68-82.
  31. Shrestha A., and A. Mahmood 2019, Review of deep learning algorithms and architectures. IEEE Access 7:53040-53065. doi:10.1109/ACCESS.2019.2912200
  32. Shruthi U., V. Nagaveni, and B.K. Raghavendra 2019, A review on machine learning classification techniques for plant disease detection. In 5th International Conference on Advanced Computing and Communication Systems (ICACCS), pp 281-284. doi:10.1109/ICACCS.2019.8728415
  33. Sibi P., S.A. Jones, and P. Siddarth 2013, Analysis of different activation functions using back propagation neural networks. J Theor Appl Inf Technol 47:1264-1268
  34. Singh R., N. Sharma, and R. Gupta 2023, Proposed CNN model for tea leaf disease classification. In 2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), pp 53-60. doi:10.1109/ICAAIC56838.2023.10140680
  35. Singh V., N. Sharma, and S. Singh 2020, A review of imaging techniques for plant disease detection. Artif Intell 4:229-242. doi:10.1016/j.aiia.2020.10.002
  36. Sladojevic S., M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic 2016, Deep neural networks-based recognition of plant diseases by leaf image classification. Comput Intell Neurosci 2016:1-11. doi:10.1155/2016/3289801
  37. Szandala T. 2021, Review and comparison of commonly used activation functions for deep neural networks. In: A Bhoi, P Mallick, CM Liu, V Balas, eds, Bio-inspired Neurocomputing. Studies in Computational Intelligence, vol 903. Springer, Singapore, pp 203-224. doi:10.1007/978-981-15-5495-7_11
  38. Tian Y., and Y. Zhang 2022, A comprehensive survey on regularization strategies in machine learning. Inf Fusion 80:146-166. doi:10.1016/j.inffus.2021.11.005
  39. Tiwari R.G., A. Misra, and N. Ujjwal 2022, Image Embedding and Classification using Pre-Trained Deep Learning Architectures. In 2022 8th International Conference on Signal Processing and Communication (ICSC), pp 125-130. doi:10.1109/ICSC56524.2022.10009560
  40. Tripathi M. 2021, Analysis of convolutional neural network-based image classification techniques. J Innov Image Proc 3(2):100-117. doi:10.36548/jiip.2021.2.003
  41. Uzair M., and N. Jamil 2020, Effects of hidden layers on the efficiency of neural networks. In 2020 23rd International Multitopic Conference (INMIC), pp 1-6. doi:10.1109/INMIC50486.2020.9318195
  42. Vaishnav D., and B.R. Rao 2018, Comparison of machine learning algorithms and fruit classification using orange data mining tool. In 2018 3rd International Conference on Inventive Computation Technologies (ICICT), pp 603-607. doi:10.1109/ICICT43934.2018.9034442
  43. Xia X., C. Xu, and B. Nan 2017, Inception-v3 for flower classification. In 2017 2nd International Conference on Image, Vision, and Computing (ICIVC), pp 783-787. doi:10.1109/ICIVC.2017.7984661