EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Deep Learning Classifiers Performance via Preprocessing and Class Imbalance Approaches in a Plant Disease Detection Pipeline

Mike O. Ojo, Azlan Zahid

Agronomy · 16.03.2023 · 13 (3) · 887

DOI: 10.3390/agronomy13030887 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Agronomy, online erschienen am 16.03.2023. Verfasst von Mike O. Ojo und 1 weiteren Autor:innen. Die Arbeit wurde bisher 73-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Texas Department of Agriculture, United States Department of Agriculture (USDA)’s National Institute of Food and Agriculture (NIFA) Federal Appropriations, Texas A&M AgriLife Research, Vegetable and Fruit Improvement Center (VFIC).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The foundation of effectively predicting plant disease in the early stage using deep learning algorithms is ideal for addressing food insecurity, inevitably drawing researchers and agricultural specialists to contribute to its effectiveness. The input preprocessor, abnormalities of the data (i.e., incomplete and nonexistent features, class imbalance), classifier, and decision explanation are typical components of a plant disease detection pipeline based on deep learning that accepts an image as input and outputs a diagnosis. Data sets related to plant diseases frequently display a magnitude imbalance due to the scarcity of disease outbreaks in real field conditions. This study examines the effects of several preprocessing methods and class imbalance approaches and deep learning classifiers steps in the pipeline for detecting plant diseases on our data set. We notably want to evaluate if additional preprocessing and effective handling of data inconsistencies in the plant disease pipeline may considerably assist deep learning classifiers. The evaluation’s findings indicate that contrast limited adaptive histogram equalization (CLAHE) combined with image sharpening and generative adversarial networks (GANs)-based approach for resampling performed the best among the preprocessing and resampling techniques, with an average classification accuracy of 97.69% and an average F1-score of 97.62% when fed through a ResNet-50 as the deep learning classifier. Lastly, this study provides a general workflow of a disease detection system that allows each component to be individually focused on depending on necessity.

Förderung

  • Texas Department of Agriculture
  • United States Department of Agriculture (USDA)’s National Institute of Food and Agriculture (NIFA) Federal Appropriations
  • Texas A&M AgriLife Research, Vegetable and Fruit Improvement Center (VFIC)
  • Hatch program of the USDA-NIFA

Zitieren

APA

Ojo, M. O., & Zahid, A. (2023). Improving Deep Learning Classifiers Performance via Preprocessing and Class Imbalance Approaches in a Plant Disease Detection Pipeline. Agronomy, 13(3), 887. https://doi.org/10.3390/agronomy13030887

Vancouver

Ojo MO, Zahid A. Improving Deep Learning Classifiers Performance via Preprocessing and Class Imbalance Approaches in a Plant Disease Detection Pipeline. Agronomy. 2023;13(3):887. doi:10.3390/agronomy13030887

BibTeX
@article{Ojo2023,
  author = {Ojo, Mike O. and Zahid, Azlan},
  title = {Improving Deep Learning Classifiers Performance via Preprocessing and Class Imbalance Approaches in a Plant Disease Detection Pipeline},
  journal = {Agronomy},
  year = {2023},
  volume = {13},
  number = {3},
  pages = {887},
  doi = {10.3390/agronomy13030887}
}
Kostenlos starten →