Design and Implementation of Crop Disease Image Classification System Using Complex Environmental Information and Data Augmentation 


Vol. 48,  No. 12, pp. 1696-1705, Dec.  2023
10.7840/kics.2023.48.12.1696


PDF
  Abstract

This paper uses a KS standard-based artificial intelligence complex environmental control system. In the automatically acquired crop image data, the environmental information from inside the greenhouse is used to predict the occurrence of diseases. In addition, by using light environment information such as insolation, light transmittance, and scattered light, crop diseases that were difficult to detect in the greenhouse demonstration environment were solved by applying pre-processing techniques such as the image conversion enhancement technique and fine parameter adjustment. As a result, the disease detection rate, which was 92.5% in 2020 in the existing demonstration environment, was raised to 95.2%. This was improved by more than 6.2%p when compared with the 89% maximum detection accuracy of the deep learning disease prediction model using keras. In other words, considering that the unseen data acquired from an external environment rather than an environment controlled by a laboratory was used (Practical outcome), it can be said that the disease classification accuracy is very high.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

T. Kim, J. Baek, D. Im, M. Kim, S. Park, J. Lee, "Design and Implementation of Crop Disease Image Classification System Using Complex Environmental Information and Data Augmentation," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 12, pp. 1696-1705, 2023. DOI: 10.7840/kics.2023.48.12.1696.

[ACM Style]

Tae-Hyun Kim, Jeong-Hyun Baek, Dong-Hyeok Im, Man-Jung Kim, Seong-Jin Park, and Jeong-Ho Lee. 2023. Design and Implementation of Crop Disease Image Classification System Using Complex Environmental Information and Data Augmentation. The Journal of Korean Institute of Communications and Information Sciences, 48, 12, (2023), 1696-1705. DOI: 10.7840/kics.2023.48.12.1696.

[KICS Style]

Tae-Hyun Kim, Jeong-Hyun Baek, Dong-Hyeok Im, Man-Jung Kim, Seong-Jin Park, Jeong-Ho Lee, "Design and Implementation of Crop Disease Image Classification System Using Complex Environmental Information and Data Augmentation," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 12, pp. 1696-1705, 12. 2023. (https://doi.org/10.7840/kics.2023.48.12.1696)
Vol. 48, No. 12 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880