Efficient Classification of Strawberry Diseases Using Fusion of Foreground and Background Information 


Vol. 45,  No. 5, pp. 775-782, May  2020
10.7840/kics.2020.45.5.775


PDF
  Abstract

Research related to the application of artificial intelligence models to the agricultural area is very active. In this paper, we propose a model that efficiently classifies strawberry diseases with the simplified network of fewer parameters due to the fusion of foreground and background information in a deep learning model. The proposed model divides learned image features into foreground and background ones, and captures the mutual relations between two areas, so that the classification might be efficient even with fewer parameters. In the proposed method, data augmentation is applied to train a network from a small amount of gathered strawberry image data, and fine-tuning is performed after transfer learning of the weights pre-trained with ImageNet dataset. The proposed method has achieved an accuracy of 95.6% in the classification problem of strawberry diseases of seven categories.

  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.


  Cite this article

[IEEE Style]

D. Kim, T. Kim, J. Lee, "Efficient Classification of Strawberry Diseases Using Fusion of Foreground and Background Information," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 5, pp. 775-782, 2020. DOI: 10.7840/kics.2020.45.5.775.

[ACM Style]

Dong-Hoon Kim, Taehyun Kim, and Joonwhoan Lee. 2020. Efficient Classification of Strawberry Diseases Using Fusion of Foreground and Background Information. The Journal of Korean Institute of Communications and Information Sciences, 45, 5, (2020), 775-782. DOI: 10.7840/kics.2020.45.5.775.

[KICS Style]

Dong-Hoon Kim, Taehyun Kim, Joonwhoan Lee, "Efficient Classification of Strawberry Diseases Using Fusion of Foreground and Background Information," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 5, pp. 775-782, 5. 2020. (https://doi.org/10.7840/kics.2020.45.5.775)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880