Smart Media Journal (스마트미디어저널)

THE KOREAN INSTITUTE OF SMART MEDIA (한국스마트미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Strawberry disease diagnosis service using EfficientNet

EfficientNet 활용한 딸기 병해 진단 서비스

  • 이창준 (순천대학교 스마트융합학부 멀티미디어공학전공) ;
  • 김진성 (순천대학교 스마트융합학부 멀티미디어공학전공) ;
  • 박준 (순천대학교 스마트융합학부 멀티미디어공학전공) ;
  • 김준영 (순천대학교 스마트융합학부 멀티미디어공학전공) ;
  • 박성욱 (순천대학교 스마트융합학부 멀티미디어공학전공) ;
  • 정세훈 (안동대학교 창의융합학부) ;
  • 심춘보 (순천대학교 스마트융합학부 멀티미디어공학전공)
  • Received : 2022.06.03
  • Accepted : 2022.07.05
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, images are automatically acquired to control the initial disease of strawberries among facility cultivation crops, and disease analysis is performed using the EfficientNet model to inform farmers of disease status, and disease diagnosis service is proposed by experts. It is possible to obtain an image of the strawberry growth stage and quickly receive expert feedback after transmitting the disease diagnosis analysis results to farmers applications using the learned EfficientNet model. As a data set, farmers who are actually operating facility cultivation were recruited and images were acquired using the system, and the problem of lack of data was solved by using the draft image taken with a cell phone. Experimental results show that the accuracy of EfficientNet B0 to B7 is similar, so we adopt B0 with the fastest inference speed. For performance improvement, Fine-tuning was performed using a pre-trained model with ImageNet, and rapid performance improvement was confirmed from 100 Epoch. The proposed service is expected to increase production by quickly detecting initial diseases.

본 논문에서는 시설재배 작물 중 딸기의 초기 병해를 방제하고자 이미지를 자동으로 취득하고, EfficientNet 모델을 활용해 병해를 분석하여 농민에게 병해 여부를 알려주고, 전문가를 통한 병해 진단 서비스를 제안한다. 딸기 생육단계의 이미지를 취득하고, 학습된 EfficientNet 모델을 활용해 병해 진단 분석결과를 농민의 애플리케이션으로 전송 후 전문가의 피드백을 신속하게 받을 수 있다. 데이터 세트로는 실제 시설재배를 운영하는 농민을 섭외하여 시스템을 이용해 이미지를 취득하였고, 핸드폰으로 촬영한 이미지의 초안을 활용하여 데이터가 부족한 문제를 해결했다. 실험 결과 EfficientNet B0부터 B7까지의 정확도는 유사하여 추론 속도가 가장 빠른 B0를 채택했다. 성능향상을 위해 ImageNet으로 사전학습 된 모델을 사용해 Fine-tuning 했고, 100 Epoch부터 급격한 성능향상을 확인했다. 제안하는 서비스는 초기 병해를 빠르게 탐지하여 생산량을 증대시킬 것으로 기대한다.

Keywords

Acknowledgement

본 연구는 2020년도 정부(교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임 (No. 2020R1I1A3054843) 본 연구는 과학기술정보통신부 및 정보통신기획평가원의 지역지능화혁신인재양성(Grand ICT연구센터) 사업의 연구결과로 수행되었음 (IITP-2022-2020-0-01489)

References

  1. J.W. Oh, H.K. Kim, Il-Tae Kim, "Design and Implementation of Fruit harvest time Predicting System based on Machine Learning," Smart Media Journal, Vol. 8, No. 1, pp. 73-81, Mar. 2019.
  2. M.H. Nam, Y.N. Jeon, H.C. Lee, H.D. Lee, and H.K. Kang, "Comparative Analysis between Healthy and Powdery Mildew-infected Plants of Strawberry Cultivar Seolhyang," Research in Plant Disease, Vol. 18, No. 2, pp. 80-85, Jun. 2012. https://doi.org/10.5423/RPD.2012.18.2.080
  3. J. Park, J.Y. Kim, S.W. Park, S.H. Jung, C.B. Sim, "Development of ResNet base Crop Growth Stage Estimation Model," Smart Media Journal, Vol. 11, No. 2, pp. 53-62, Mar. 2022.
  4. M.H Nam, H.S Kim, T.I Kim, E.M Lee, "Comparison of Environmental-Friendly and Chemical Spray Calendar for Controlling Diseases and Insect Pest of Strawberry during Nuresery Seasons," Research in Plant Disease, Vol. 21, No. 4, pp. 273-279, Dec. 2015. https://doi.org/10.5423/RPD.2015.21.4.273
  5. S.J. Kim, H.S. Kim, "Deep learning-based Automatic Weed Detection on Onion Field," Smart Media Journal, Vol. 7, No. 3, pp. 16-21, Sep. 2018. https://doi.org/10.30693/SMJ.2018.7.3.16
  6. C.J. Lee, J.S. Kim, J.Y. Kim, J. Park, S.W. Park, and C.B. Sim, "Design of Facility Crops Data Analysis Platform based on Drone for Pest Detection," Proceeding of Fall Conference of the Korea Multimedia Society, Vol. 24, No. 2, pp. 48-50, Nov. 2021.
  7. M.G. Kim, "Tomato Crop Disease Classification Using an Ensemble Approach Based on a Deep Neural Network," Journal of Korea Multimedia Society, Vol. 23, No. 10, pp. 1250-1257, Oct. 2020. https://doi.org/10.9717/KMMS.2020.23.10.1250
  8. M. Tan, and Q. Le, "Efficientnet: Rethinking model scaling for convolutional neural networks," In International Conference on Machine Learning (PMLR), pp. 6105-6114, 2019.
  9. H.S. Ham, and H.J. J, "A Development of Rose Leaf Disease Classification System using Convolutional Neural Network," The Transactions of the Korean Institute of Electrical Engineers, Vol. 69, No. 7, pp. 1040-1045, Jul. 2020. https://doi.org/10.5370/kiee.2020.69.7.1040
  10. C. Szegedy, S Ioffe, V. Vanhoucke, A.A. Alemi, "Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning," In Thirty-first AAAI conference on artificial inteeligencem, Sanfrancisco, USA, pp. 4278-4284, Feb. 2017.
  11. K.H. Jo, S.H. Jung, and C.B. Sim, "A Study of Shiitake Disease and Pest Image Analysis based on Deep Learning," Journal of Korea Multimedia Society, Vol. 23, No. 1, 2020. https://doi.org/10.9717/kmms.2020.23.1.031
  12. A. Krizhevsky, I. Sutskever, and G.E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Advances in neural information processing systems, pp. 1106-1114, 2012.
  13. J.Y. Kang, I.K. Kim, H.S. Lim, and J.H. Gwak, "A Crack Detection of Wooden Cultural Assets using EfficientNet model," Proceedings of the Korean Society of Computer Information Conference, Vol. 29, No. 2, pp. 125-127, 2021.