Automatic Clustering and Classification of Coffee Leaf Diseases Based on an Extended Kernel Density Estimation Approach
The current methods of classifying plant disease images are mainly affected by the training phase and the characteristics of the target dataset. Collecting plant samples during different leaf life cycle infection stages is time-consuming. However, these samples may have multiple symptoms that share...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Plants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2223-7747/12/8/1603 |
| _version_ | 1797603834592231424 |
|---|---|
| author | Reem Ibrahim Hasan Suhaila Mohd Yusuf Mohd Shafry Mohd Rahim Laith Alzubaidi |
| author_facet | Reem Ibrahim Hasan Suhaila Mohd Yusuf Mohd Shafry Mohd Rahim Laith Alzubaidi |
| author_sort | Reem Ibrahim Hasan |
| collection | DOAJ |
| description | The current methods of classifying plant disease images are mainly affected by the training phase and the characteristics of the target dataset. Collecting plant samples during different leaf life cycle infection stages is time-consuming. However, these samples may have multiple symptoms that share the same features but with different densities. The manual labelling of such samples demands exhaustive labour work that may contain errors and corrupt the training phase. Furthermore, the labelling and the annotation consider the dominant disease and neglect the minor disease, leading to misclassification. This paper proposes a fully automated leaf disease diagnosis framework that extracts the region of interest based on a modified colour process, according to which syndrome is self-clustered using an extended Gaussian kernel density estimation and the probability of the nearest shared neighbourhood. Each group of symptoms is presented to the classifier independently. The objective is to cluster symptoms using a nonparametric method, decrease the classification error, and reduce the need for a large-scale dataset to train the classifier. To evaluate the efficiency of the proposed framework, coffee leaf datasets were selected to assess the framework performance due to a wide variety of feature demonstrations at different levels of infections. Several kernels with their appropriate bandwidth selector were compared. The best probabilities were achieved by the proposed extended Gaussian kernel, which connects the neighbouring lesions in one symptom cluster, where there is no need for any influencing set that guides toward the correct cluster. Clusters are presented with an equal priority to a ResNet50 classifier, so misclassification is reduced with an accuracy of up to 98%. |
| first_indexed | 2024-03-11T04:37:42Z |
| format | Article |
| id | doaj.art-d585ae2504ef403d926d268471353b9e |
| institution | Directory Open Access Journal |
| issn | 2223-7747 |
| language | English |
| last_indexed | 2024-03-11T04:37:42Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Plants |
| spelling | doaj.art-d585ae2504ef403d926d268471353b9e2023-11-17T20:59:02ZengMDPI AGPlants2223-77472023-04-01128160310.3390/plants12081603Automatic Clustering and Classification of Coffee Leaf Diseases Based on an Extended Kernel Density Estimation ApproachReem Ibrahim Hasan0Suhaila Mohd Yusuf1Mohd Shafry Mohd Rahim2Laith Alzubaidi3School of Computing, Faculty of Computing, Universiti Teknologi Malaysia, Skudai 81310, Johor, MalaysiaSchool of Computing, Faculty of Computing, Universiti Teknologi Malaysia, Skudai 81310, Johor, MalaysiaSchool of Computing, Faculty of Computing, Universiti Teknologi Malaysia, Skudai 81310, Johor, MalaysiaSchool of Mechanical, Medical and Process Engineering, Queensland University of Technology, Brisbane, QLD 4000, AustraliaThe current methods of classifying plant disease images are mainly affected by the training phase and the characteristics of the target dataset. Collecting plant samples during different leaf life cycle infection stages is time-consuming. However, these samples may have multiple symptoms that share the same features but with different densities. The manual labelling of such samples demands exhaustive labour work that may contain errors and corrupt the training phase. Furthermore, the labelling and the annotation consider the dominant disease and neglect the minor disease, leading to misclassification. This paper proposes a fully automated leaf disease diagnosis framework that extracts the region of interest based on a modified colour process, according to which syndrome is self-clustered using an extended Gaussian kernel density estimation and the probability of the nearest shared neighbourhood. Each group of symptoms is presented to the classifier independently. The objective is to cluster symptoms using a nonparametric method, decrease the classification error, and reduce the need for a large-scale dataset to train the classifier. To evaluate the efficiency of the proposed framework, coffee leaf datasets were selected to assess the framework performance due to a wide variety of feature demonstrations at different levels of infections. Several kernels with their appropriate bandwidth selector were compared. The best probabilities were achieved by the proposed extended Gaussian kernel, which connects the neighbouring lesions in one symptom cluster, where there is no need for any influencing set that guides toward the correct cluster. Clusters are presented with an equal priority to a ResNet50 classifier, so misclassification is reduced with an accuracy of up to 98%.https://www.mdpi.com/2223-7747/12/8/1603kernel density estimationshared neighbourhoodoverlapping diseasesmap generationlesions fragmentation |
| spellingShingle | Reem Ibrahim Hasan Suhaila Mohd Yusuf Mohd Shafry Mohd Rahim Laith Alzubaidi Automatic Clustering and Classification of Coffee Leaf Diseases Based on an Extended Kernel Density Estimation Approach Plants kernel density estimation shared neighbourhood overlapping diseases map generation lesions fragmentation |
| title | Automatic Clustering and Classification of Coffee Leaf Diseases Based on an Extended Kernel Density Estimation Approach |
| title_full | Automatic Clustering and Classification of Coffee Leaf Diseases Based on an Extended Kernel Density Estimation Approach |
| title_fullStr | Automatic Clustering and Classification of Coffee Leaf Diseases Based on an Extended Kernel Density Estimation Approach |
| title_full_unstemmed | Automatic Clustering and Classification of Coffee Leaf Diseases Based on an Extended Kernel Density Estimation Approach |
| title_short | Automatic Clustering and Classification of Coffee Leaf Diseases Based on an Extended Kernel Density Estimation Approach |
| title_sort | automatic clustering and classification of coffee leaf diseases based on an extended kernel density estimation approach |
| topic | kernel density estimation shared neighbourhood overlapping diseases map generation lesions fragmentation |
| url | https://www.mdpi.com/2223-7747/12/8/1603 |
| work_keys_str_mv | AT reemibrahimhasan automaticclusteringandclassificationofcoffeeleafdiseasesbasedonanextendedkerneldensityestimationapproach AT suhailamohdyusuf automaticclusteringandclassificationofcoffeeleafdiseasesbasedonanextendedkerneldensityestimationapproach AT mohdshafrymohdrahim automaticclusteringandclassificationofcoffeeleafdiseasesbasedonanextendedkerneldensityestimationapproach AT laithalzubaidi automaticclusteringandclassificationofcoffeeleafdiseasesbasedonanextendedkerneldensityestimationapproach |