Cargando…
Coffee Disease Visualization and Classification
Deep learning architectures are widely used in state-of-the-art image classification tasks. Deep learning has enhanced the ability to automatically detect and classify plant diseases. However, in practice, disease classification problems are treated as black-box methods. Thus, it is difficult to tru...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8235481/ https://www.ncbi.nlm.nih.gov/pubmed/34205610 http://dx.doi.org/10.3390/plants10061257 |
_version_ | 1783714328680071168 |
---|---|
author | Yebasse, Milkisa Shimelis, Birhanu Warku, Henok Ko, Jaepil Cheoi, Kyung Joo |
author_facet | Yebasse, Milkisa Shimelis, Birhanu Warku, Henok Ko, Jaepil Cheoi, Kyung Joo |
author_sort | Yebasse, Milkisa |
collection | PubMed |
description | Deep learning architectures are widely used in state-of-the-art image classification tasks. Deep learning has enhanced the ability to automatically detect and classify plant diseases. However, in practice, disease classification problems are treated as black-box methods. Thus, it is difficult to trust the model that it truly identifies the region of the disease in the image; it may simply use unrelated surroundings for classification. Visualization techniques can help determine important areas for the model by highlighting the region responsible for the classification. In this study, we present a methodology for visualizing coffee diseases using different visualization approaches. Our goal is to visualize aspects of a coffee disease to obtain insight into what the model “sees” as it learns to classify healthy and non-healthy images. In addition, visualization helped us identify misclassifications and led us to propose a guided approach for coffee disease classification. The guided approach achieved a classification accuracy of 98% compared to the 77% of naïve approach on the Robusta coffee leaf image dataset. The visualization methods considered in this study were Grad-CAM, Grad-CAM++, and Score-CAM. We also provided a visual comparison of the visualization methods. |
format | Online Article Text |
id | pubmed-8235481 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-82354812021-06-27 Coffee Disease Visualization and Classification Yebasse, Milkisa Shimelis, Birhanu Warku, Henok Ko, Jaepil Cheoi, Kyung Joo Plants (Basel) Article Deep learning architectures are widely used in state-of-the-art image classification tasks. Deep learning has enhanced the ability to automatically detect and classify plant diseases. However, in practice, disease classification problems are treated as black-box methods. Thus, it is difficult to trust the model that it truly identifies the region of the disease in the image; it may simply use unrelated surroundings for classification. Visualization techniques can help determine important areas for the model by highlighting the region responsible for the classification. In this study, we present a methodology for visualizing coffee diseases using different visualization approaches. Our goal is to visualize aspects of a coffee disease to obtain insight into what the model “sees” as it learns to classify healthy and non-healthy images. In addition, visualization helped us identify misclassifications and led us to propose a guided approach for coffee disease classification. The guided approach achieved a classification accuracy of 98% compared to the 77% of naïve approach on the Robusta coffee leaf image dataset. The visualization methods considered in this study were Grad-CAM, Grad-CAM++, and Score-CAM. We also provided a visual comparison of the visualization methods. MDPI 2021-06-21 /pmc/articles/PMC8235481/ /pubmed/34205610 http://dx.doi.org/10.3390/plants10061257 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Yebasse, Milkisa Shimelis, Birhanu Warku, Henok Ko, Jaepil Cheoi, Kyung Joo Coffee Disease Visualization and Classification |
title | Coffee Disease Visualization and Classification |
title_full | Coffee Disease Visualization and Classification |
title_fullStr | Coffee Disease Visualization and Classification |
title_full_unstemmed | Coffee Disease Visualization and Classification |
title_short | Coffee Disease Visualization and Classification |
title_sort | coffee disease visualization and classification |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8235481/ https://www.ncbi.nlm.nih.gov/pubmed/34205610 http://dx.doi.org/10.3390/plants10061257 |
work_keys_str_mv | AT yebassemilkisa coffeediseasevisualizationandclassification AT shimelisbirhanu coffeediseasevisualizationandclassification AT warkuhenok coffeediseasevisualizationandclassification AT kojaepil coffeediseasevisualizationandclassification AT cheoikyungjoo coffeediseasevisualizationandclassification |