Automatic Identification of Peanut-Leaf Diseases Based on Stack Ensemble
Peanut is an important food crop, and diseases of its leaves can directly reduce its yield and quality. In order to solve the problem of automatic identification of peanut-leaf diseases, this paper uses a traditional machine-learning method to ensemble the output of a deep learning model to identify...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/4/1950 |
| _version_ | 1797395554459713536 |
|---|---|
| author | Haixia Qi Yu Liang Quanchen Ding Jun Zou |
| author_facet | Haixia Qi Yu Liang Quanchen Ding Jun Zou |
| author_sort | Haixia Qi |
| collection | DOAJ |
| description | Peanut is an important food crop, and diseases of its leaves can directly reduce its yield and quality. In order to solve the problem of automatic identification of peanut-leaf diseases, this paper uses a traditional machine-learning method to ensemble the output of a deep learning model to identify diseases of peanut leaves. The identification of peanut-leaf diseases included healthy leaves, rust disease on a single leaf, leaf-spot disease on a single leaf, scorch disease on a single leaf, and both rust disease and scorch disease on a single leaf. Three types of data-augmentation methods were used: image flipping, rotation, and scaling. In this experiment, the deep-learning model had a higher accuracy than the traditional machine-learning methods. Moreover, the deep-learning model achieved better performance when using data augmentation and a stacking ensemble. After ensemble by logistic regression, the accuracy of residual network with 50 layers (ResNet50) was as high as 97.59%, and the <i>F</i>1 score of dense convolutional network with 121 layers (DenseNet121) was as high as 90.50. The deep-learning model used in this experiment had the greatest improvement in <i>F</i>1 score after the logistic regression ensemble. Deep-learning networks with deeper network layers like ResNet50 and DenseNet121 performed better in this experiment. This study can provide a reference for the identification of peanut-leaf diseases. |
| first_indexed | 2024-03-09T00:37:12Z |
| format | Article |
| id | doaj.art-236e318e7f1243c68f97c9d7efd1daa4 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T00:37:12Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-236e318e7f1243c68f97c9d7efd1daa42023-12-11T18:03:18ZengMDPI AGApplied Sciences2076-34172021-02-01114195010.3390/app11041950Automatic Identification of Peanut-Leaf Diseases Based on Stack EnsembleHaixia Qi0Yu Liang1Quanchen Ding2Jun Zou3College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaDepartment of Electrical & Computer Engineering, College of Engineering, University of Washington, Seattle, WA 98195-2500, USACollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaPeanut is an important food crop, and diseases of its leaves can directly reduce its yield and quality. In order to solve the problem of automatic identification of peanut-leaf diseases, this paper uses a traditional machine-learning method to ensemble the output of a deep learning model to identify diseases of peanut leaves. The identification of peanut-leaf diseases included healthy leaves, rust disease on a single leaf, leaf-spot disease on a single leaf, scorch disease on a single leaf, and both rust disease and scorch disease on a single leaf. Three types of data-augmentation methods were used: image flipping, rotation, and scaling. In this experiment, the deep-learning model had a higher accuracy than the traditional machine-learning methods. Moreover, the deep-learning model achieved better performance when using data augmentation and a stacking ensemble. After ensemble by logistic regression, the accuracy of residual network with 50 layers (ResNet50) was as high as 97.59%, and the <i>F</i>1 score of dense convolutional network with 121 layers (DenseNet121) was as high as 90.50. The deep-learning model used in this experiment had the greatest improvement in <i>F</i>1 score after the logistic regression ensemble. Deep-learning networks with deeper network layers like ResNet50 and DenseNet121 performed better in this experiment. This study can provide a reference for the identification of peanut-leaf diseases.https://www.mdpi.com/2076-3417/11/4/1950peanut-leaf diseasesdeep learningconvolutional neural networkidentification |
| spellingShingle | Haixia Qi Yu Liang Quanchen Ding Jun Zou Automatic Identification of Peanut-Leaf Diseases Based on Stack Ensemble Applied Sciences peanut-leaf diseases deep learning convolutional neural network identification |
| title | Automatic Identification of Peanut-Leaf Diseases Based on Stack Ensemble |
| title_full | Automatic Identification of Peanut-Leaf Diseases Based on Stack Ensemble |
| title_fullStr | Automatic Identification of Peanut-Leaf Diseases Based on Stack Ensemble |
| title_full_unstemmed | Automatic Identification of Peanut-Leaf Diseases Based on Stack Ensemble |
| title_short | Automatic Identification of Peanut-Leaf Diseases Based on Stack Ensemble |
| title_sort | automatic identification of peanut leaf diseases based on stack ensemble |
| topic | peanut-leaf diseases deep learning convolutional neural network identification |
| url | https://www.mdpi.com/2076-3417/11/4/1950 |
| work_keys_str_mv | AT haixiaqi automaticidentificationofpeanutleafdiseasesbasedonstackensemble AT yuliang automaticidentificationofpeanutleafdiseasesbasedonstackensemble AT quanchending automaticidentificationofpeanutleafdiseasesbasedonstackensemble AT junzou automaticidentificationofpeanutleafdiseasesbasedonstackensemble |