The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Study on Image Use for Plant Disease Classification

작물의 병충해 분류를 위한 이미지 활용 방법 연구

  • 정성호 (상명대학교 휴먼지능로봇공학과) ;
  • 한정은 (상명대학교 휴먼지능로봇공학과) ;
  • 정성균 (상명대학교 휴먼지능로봇공학과) ;
  • 봉재환 (상명대학교 휴먼지능로봇공학과)
  • Received : 2022.01.19
  • Accepted : 2022.04.17
  • Published : 2022.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

It is worth verifying the effectiveness of data integration between data with different features. This study investigated whether the data integration affects the accuracy of deep neural network (DNN), and which integration method shows the best improvement. This study used two different public datasets. One public dataset was taken in an actual farm in India. And another was taken in a laboratory environment in Korea. Leaf images were selected from two different public datasets to have five classes which includes normal and four different types of plant diseases. DNN used pre-trained VGG16 as a feature extractor and multi-layer perceptron as a classifier. Data were integrated into three different ways to be used for the training process. DNN was trained in a supervised manner via the integrated data. The trained DNN was evaluated by using a test dataset taken in an actual farm. DNN shows the best accuracy for the test dataset when DNN was first trained by images taken in the laboratory environment and then trained by images taken in the actual farm. The results show that data integration between plant images taken in a different environment helps improve the performance of deep neural networks. And the results also confirmed that independent use of plant images taken in different environments during the training process is more effective in improving the performance of DNN.

서로 다른 특징을 가지는 이미지를 통합하여 작물의 병충해 분류를 위한 심층신경망을 훈련하는 것이 학습 결과에 어떤 영향을 미치는지 확인하고, 심층신경망의 학습 결과를 개선할 수 있는 이미지 통합방법에 대해 실험하였다. 실험을 위해 두 종류의 작물 이미지 공개 데이터가 사용되었다. 하나는 인도의 실제 농장 환경에서 촬영된 작물 이미지이고 다른 하나는 한국의 실험실 환경에서 촬영한 작물 이미지였다. 작물 잎 이미지는 정상인 경우와 4종류의 병충해를 포함하여 5개의 하위 범주로 구성되었다. 심층신경망은 전이학습을 통해 사전 훈련된 VGG16이 특징 추출부에 사용되었고 분류기에는 다층퍼셉트론 구조를 사용하였다. 두 공개 데이터는 세 가지 방법으로 통합되어 심층신경망의 지도학습에 사용되었다. 훈련된 심층신경망은 평가 데이터를 이용해 평가되었다. 실험 결과에 따르면 심층신경망을 실험실 환경에서 촬영한 작물 이미지로 학습한 이후에 실제 농장 환경에서 촬영한 작물 이미지로 재학습하는 경우에 가장 좋은 성능을 보였다. 서로 다른 배경의 두 공공데이터를 혼용하여 사용하면 심층신경망의 학습 결과가 좋지 않았다. 심층신경망의 학습 과정에서 여러 종류의 데이터를 사용하는 방법에 따라 심층신경망의 성능이 달라질 수 있음을 확인하였다.

Keywords

Acknowledgement

본 연구는 2021학년도 상명대학교 교내연구비를 지원받아 수행하였음

References

  1. S. Salimov and J. Yoo, "A Design of Small Scale Deep CNN Model for Facial Expression Recognition using the Low Resolution Image Datasets," J. of the Korea Institute of Electronic Communication Sciences, vol. 16, no. 1, 2021, pp. 75-80. https://doi.org/10.13067/JKIECS.2021.16.1.75
  2. S. Bak, N. Kim, M. Jeong, D. Hwang, U. Enkhjargal, B. Kim, M. Park, H. Yoon, and W. Seo, "Study on Detection Technique for Coastal Debris by using Unmanned Aerial Vehicle Remote Sensing and Object Detection Algorithm based on Deep Learning," J. of the Korea Institute of Electronic Communication Sciences, vol. 15, no. 6, 2020, pp. 1209-1216. https://doi.org/10.13067/JKIECS.2020.15.6.1209
  3. S. Bak, M. Jeong, D. Hwang, U. Enkhjargal, N. Kim, and H. Yoon., "Study on Cochlodinium polykrikoides Red tide Prediction using Deep Neural Network under Imbalanced Data," J. of the Korea Institute of Electronic Communication Sciences, vol. 14, no. 6, 2019, pp. 1161-1170. https://doi.org/10.13067/JKIECS.2019.14.6.1161
  4. S. Kim and J. Ahn, "Tomato Crop Diseases Classification Models Using Deep CNN-based Architectures," J. of the Korea Academia-Industrial cooperation Society, vol. 22, no. 5, 2021, pp. 7-14.
  5. K. Aravind, P. Raja, and R. Aniirudh, "Tomato crop disease classification using pre-trained deep learning algorithm," Procedia Computer Science, vol. 133, no. 1, 2018, pp. 1040-1047. https://doi.org/10.1016/j.procs.2018.07.070
  6. H. Ham and H. Cho, "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, 2020, pp. 1040-1045. https://doi.org/10.5370/kiee.2020.69.7.1040
  7. M. Kim and C. Choi, "Superpixel-based Apple Leaf Disease Classification using Convolutional Neural Network," J. of Broadcast Engineering, vol. 25, no. 2, 2020, pp. 208-217. https://doi.org/10.5909/JBE.2020.25.2.208
  8. S. Davinder, J. Naman, J. Pranjali, K. Pratik, K. Sudhakar, and B. Nipun, "PlantDoc: A Dataset for Visual Plant Disease Detection," Proceedings of the 7th Association for Computing Machinery India Special Interest Group On Knowledge Discovery and Data Mining Conference on Data Sciences and 25th Conference on Management of Data, Hyderabad, India, 2020, pp. 249-253.
  9. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," International Conference on Learning Representations, San Diego, CA, USA, 2015.
  10. A. Krizhevsky, I. Sutskever, and G. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, vol. 25, 2012, pp. 1097-1105.