Classifying Barako coffee leaf diseases using deep convolutional models
This work presents the application of recent Deep Convolutional Models (DCM) to classify Barako leaf diseases. Several selected DCMs performed image classification tasks using Transfer Learning and Fine-Tuning, together with data preprocessing and augmentation. The collected dataset used totals to 4...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Ahmad Dahlan
2020-07-01
|
| Series: | IJAIN (International Journal of Advances in Intelligent Informatics) |
| Subjects: | |
| Online Access: | http://ijain.org/index.php/IJAIN/article/view/495 |
| _version_ | 1818838328554815488 |
|---|---|
| author | Francis Jesmar Perez Montalbo Alexander Arsenio Hernandez |
| author_facet | Francis Jesmar Perez Montalbo Alexander Arsenio Hernandez |
| author_sort | Francis Jesmar Perez Montalbo |
| collection | DOAJ |
| description | This work presents the application of recent Deep Convolutional Models (DCM) to classify Barako leaf diseases. Several selected DCMs performed image classification tasks using Transfer Learning and Fine-Tuning, together with data preprocessing and augmentation. The collected dataset used totals to 4,667. Each labeled into four different classes, which included Coffee Leaf Rust (CLR), Cercospora Leaf Spots (CLS), Sooty Molds (SM), and Healthy Leaves (HL). The DCMs were trained using the partial 4,023 images and validated with the remaining 644. The classification results of the trained models VGG16, Xception, and ResNetV2-152 attained overall accuracies of 97%, 95%, and 91%, respectively. By comparing in terms of True Positive Rate (TPR), we found that Xception has the highest number of correct classifications of CLR, VGG16 with SM, and CLS, while ResNetV2-152 with the lowest TPR for CLR. The evaluated results indicate that the use of Deep Convolutional Models with an adequate amount of data, proper fine-tuning, preprocessing, and transfer learning can yield efficient classifiers for identifying several Barako leaf diseases. This work primarily contributes to the growing field of deep learning, specifically for helping farmers improve their diagnostic process by providing a solution that can automatically classify Barako leaf diseases. |
| first_indexed | 2024-12-19T03:36:39Z |
| format | Article |
| id | doaj.art-d416789660ca4c3286a05fdf86bcbe6f |
| institution | Directory Open Access Journal |
| issn | 2442-6571 2548-3161 |
| language | English |
| last_indexed | 2024-12-19T03:36:39Z |
| publishDate | 2020-07-01 |
| publisher | Universitas Ahmad Dahlan |
| record_format | Article |
| series | IJAIN (International Journal of Advances in Intelligent Informatics) |
| spelling | doaj.art-d416789660ca4c3286a05fdf86bcbe6f2022-12-21T20:37:23ZengUniversitas Ahmad DahlanIJAIN (International Journal of Advances in Intelligent Informatics)2442-65712548-31612020-07-016219720910.26555/ijain.v6i2.495149Classifying Barako coffee leaf diseases using deep convolutional modelsFrancis Jesmar Perez Montalbo0Alexander Arsenio Hernandez1Technological Institute of the Philippines Manila, Batangas State UniversityTechnological Institute of the Philippines ManilaThis work presents the application of recent Deep Convolutional Models (DCM) to classify Barako leaf diseases. Several selected DCMs performed image classification tasks using Transfer Learning and Fine-Tuning, together with data preprocessing and augmentation. The collected dataset used totals to 4,667. Each labeled into four different classes, which included Coffee Leaf Rust (CLR), Cercospora Leaf Spots (CLS), Sooty Molds (SM), and Healthy Leaves (HL). The DCMs were trained using the partial 4,023 images and validated with the remaining 644. The classification results of the trained models VGG16, Xception, and ResNetV2-152 attained overall accuracies of 97%, 95%, and 91%, respectively. By comparing in terms of True Positive Rate (TPR), we found that Xception has the highest number of correct classifications of CLR, VGG16 with SM, and CLS, while ResNetV2-152 with the lowest TPR for CLR. The evaluated results indicate that the use of Deep Convolutional Models with an adequate amount of data, proper fine-tuning, preprocessing, and transfer learning can yield efficient classifiers for identifying several Barako leaf diseases. This work primarily contributes to the growing field of deep learning, specifically for helping farmers improve their diagnostic process by providing a solution that can automatically classify Barako leaf diseases.http://ijain.org/index.php/IJAIN/article/view/495deep learningconvolutional neural networksclassificationleaf diseasebarako coffee |
| spellingShingle | Francis Jesmar Perez Montalbo Alexander Arsenio Hernandez Classifying Barako coffee leaf diseases using deep convolutional models IJAIN (International Journal of Advances in Intelligent Informatics) deep learning convolutional neural networks classification leaf disease barako coffee |
| title | Classifying Barako coffee leaf diseases using deep convolutional models |
| title_full | Classifying Barako coffee leaf diseases using deep convolutional models |
| title_fullStr | Classifying Barako coffee leaf diseases using deep convolutional models |
| title_full_unstemmed | Classifying Barako coffee leaf diseases using deep convolutional models |
| title_short | Classifying Barako coffee leaf diseases using deep convolutional models |
| title_sort | classifying barako coffee leaf diseases using deep convolutional models |
| topic | deep learning convolutional neural networks classification leaf disease barako coffee |
| url | http://ijain.org/index.php/IJAIN/article/view/495 |
| work_keys_str_mv | AT francisjesmarperezmontalbo classifyingbarakocoffeeleafdiseasesusingdeepconvolutionalmodels AT alexanderarseniohernandez classifyingbarakocoffeeleafdiseasesusingdeepconvolutionalmodels |