Classification and Analysis of <em>Agaricus bisporus</em> Diseases with Pre-Trained Deep Learning Models
This research evaluates 20 advanced convolutional neural network (CNN) architectures for classifying mushroom diseases in <i>Agaricus bisporus</i>, utilizing a custom dataset of 3195 images (2464 infected and 731 healthy mushrooms) captured under uniform white-light conditions. The consi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/15/1/226 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589412227088384 |
|---|---|
| author | Umit Albayrak Adem Golcuk Sinan Aktas Ugur Coruh Sakir Tasdemir Omer Kaan Baykan |
| author_facet | Umit Albayrak Adem Golcuk Sinan Aktas Ugur Coruh Sakir Tasdemir Omer Kaan Baykan |
| author_sort | Umit Albayrak |
| collection | DOAJ |
| description | This research evaluates 20 advanced convolutional neural network (CNN) architectures for classifying mushroom diseases in <i>Agaricus bisporus</i>, utilizing a custom dataset of 3195 images (2464 infected and 731 healthy mushrooms) captured under uniform white-light conditions. The consistent illumination in the dataset enhances the robustness and practical usability of the assessed models. Using a weighted scoring system that incorporates precision, recall, F1-score, area under the ROC curve (AUC), and average precision (AP), ResNet-50 achieved the highest overall score of 99.70%, demonstrating outstanding performance across all disease categories. DenseNet-201 and DarkNet-53 followed closely, confirming their reliability in classification tasks with high recall and precision values. Confusion matrices and ROC curves further validated the classification capabilities of the models. These findings underscore the potential of CNN-based approaches for accurate and efficient early detection of mushroom diseases, contributing to more sustainable and data-driven agricultural practices. |
| format | Article |
| id | doaj-art-85228abbcba8471687b230803b83c4ad |
| institution | Kabale University |
| issn | 2073-4395 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-85228abbcba8471687b230803b83c4ad2025-01-24T13:17:15ZengMDPI AGAgronomy2073-43952025-01-0115122610.3390/agronomy15010226Classification and Analysis of <em>Agaricus bisporus</em> Diseases with Pre-Trained Deep Learning ModelsUmit Albayrak0Adem Golcuk1Sinan Aktas2Ugur Coruh3Sakir Tasdemir4Omer Kaan Baykan5Ilgin Vocational School, Selcuk University, Konya 42600, TurkeyDepartment of Computer Engineering, Selcuk University, Konya 42031, TurkeyDepartment of Biology, Selcuk University, Konya 42031, TurkeyDepartment of Computer Engineering, Recep Tayyip Erdoğan University, Rize 53020, TurkeyDepartment of Computer Engineering, Selcuk University, Konya 42031, TurkeyDepartment of Computer Engineering, Konya Technical University, Konya 42250, TurkeyThis research evaluates 20 advanced convolutional neural network (CNN) architectures for classifying mushroom diseases in <i>Agaricus bisporus</i>, utilizing a custom dataset of 3195 images (2464 infected and 731 healthy mushrooms) captured under uniform white-light conditions. The consistent illumination in the dataset enhances the robustness and practical usability of the assessed models. Using a weighted scoring system that incorporates precision, recall, F1-score, area under the ROC curve (AUC), and average precision (AP), ResNet-50 achieved the highest overall score of 99.70%, demonstrating outstanding performance across all disease categories. DenseNet-201 and DarkNet-53 followed closely, confirming their reliability in classification tasks with high recall and precision values. Confusion matrices and ROC curves further validated the classification capabilities of the models. These findings underscore the potential of CNN-based approaches for accurate and efficient early detection of mushroom diseases, contributing to more sustainable and data-driven agricultural practices.https://www.mdpi.com/2073-4395/15/1/226<i>Agaricus bisporus</i>mushroom diseasesdeep learningimage processingprecision agriculturesmart farming |
| spellingShingle | Umit Albayrak Adem Golcuk Sinan Aktas Ugur Coruh Sakir Tasdemir Omer Kaan Baykan Classification and Analysis of <em>Agaricus bisporus</em> Diseases with Pre-Trained Deep Learning Models Agronomy <i>Agaricus bisporus</i> mushroom diseases deep learning image processing precision agriculture smart farming |
| title | Classification and Analysis of <em>Agaricus bisporus</em> Diseases with Pre-Trained Deep Learning Models |
| title_full | Classification and Analysis of <em>Agaricus bisporus</em> Diseases with Pre-Trained Deep Learning Models |
| title_fullStr | Classification and Analysis of <em>Agaricus bisporus</em> Diseases with Pre-Trained Deep Learning Models |
| title_full_unstemmed | Classification and Analysis of <em>Agaricus bisporus</em> Diseases with Pre-Trained Deep Learning Models |
| title_short | Classification and Analysis of <em>Agaricus bisporus</em> Diseases with Pre-Trained Deep Learning Models |
| title_sort | classification and analysis of em agaricus bisporus em diseases with pre trained deep learning models |
| topic | <i>Agaricus bisporus</i> mushroom diseases deep learning image processing precision agriculture smart farming |
| url | https://www.mdpi.com/2073-4395/15/1/226 |
| work_keys_str_mv | AT umitalbayrak classificationandanalysisofemagaricusbisporusemdiseaseswithpretraineddeeplearningmodels AT ademgolcuk classificationandanalysisofemagaricusbisporusemdiseaseswithpretraineddeeplearningmodels AT sinanaktas classificationandanalysisofemagaricusbisporusemdiseaseswithpretraineddeeplearningmodels AT ugurcoruh classificationandanalysisofemagaricusbisporusemdiseaseswithpretraineddeeplearningmodels AT sakirtasdemir classificationandanalysisofemagaricusbisporusemdiseaseswithpretraineddeeplearningmodels AT omerkaanbaykan classificationandanalysisofemagaricusbisporusemdiseaseswithpretraineddeeplearningmodels |