Image-Based Hot Pepper Disease and Pest Diagnosis Using Transfer Learning and Fine-Tuning

Yeong Hyeon Gu; Helin Yin; Dong Jin; Jong-Han Park; Seong Joon Yoo

doi:10.3389/fpls.2021.724487

Image-Based Hot Pepper Disease and Pest Diagnosis Using Transfer Learning and Fine-Tuning

Front Plant Sci. 2021 Dec 16:12:724487. doi: 10.3389/fpls.2021.724487. eCollection 2021.

Authors

Yeong Hyeon Gu¹, Helin Yin¹, Dong Jin¹, Jong-Han Park², Seong Joon Yoo¹

Affiliations

¹ Department of Computer Science and Engineering, Sejong University, Seoul, South Korea.
² Horticultural and Herbal Crop Environment Division, National Institute of Horticultural and Herbal Science, Rural Development Administration, Wanju, South Korea.

Abstract

Past studies of plant disease and pest recognition used classification methods that presented a singular recognition result to the user. Unfortunately, incorrect recognition results may be output, which may lead to further crop damage. To address this issue, there is a need for a system that suggest several candidate results and allow the user to make the final decision. In this study, we propose a method for diagnosing plant diseases and identifying pests using deep features based on transfer learning. To extract deep features, we employ pre-trained VGG and ResNet 50 architectures based on the ImageNet dataset, and output disease and pest images similar to a query image via a k-nearest-neighbor algorithm. In this study, we use a total of 23,868 images of 19 types of hot-pepper diseases and pests, for which, the proposed model achieves accuracies of 96.02 and 99.61%, respectively. We also measure the effects of fine-tuning and distance metrics. The results show that the use of fine-tuning-based deep features increases accuracy by approximately 0.7-7.38%, and the Bray-Curtis distance achieves an accuracy of approximately 0.65-1.51% higher than the Euclidean distance.

Keywords: deep feature; distance metric; fine-tuning; hot pepper; k-nearest neighbors; transfer learning.