Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models
Proper plant leaf disease (PLD) detection is challenging in complex backgrounds and under different capture conditions. For this reason, initially, modified adaptive centroid-based segmentation (ACS) is used to trace the proper region of interest (ROI). Automatic initialization of the number of clus...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/13/3/511 |
| _version_ | 1797540568410095616 |
|---|---|
| author | Syed Mohammad Minhaz Hossain Kaushik Deb Pranab Kumar Dhar Takeshi Koshiba |
| author_facet | Syed Mohammad Minhaz Hossain Kaushik Deb Pranab Kumar Dhar Takeshi Koshiba |
| author_sort | Syed Mohammad Minhaz Hossain |
| collection | DOAJ |
| description | Proper plant leaf disease (PLD) detection is challenging in complex backgrounds and under different capture conditions. For this reason, initially, modified adaptive centroid-based segmentation (ACS) is used to trace the proper region of interest (ROI). Automatic initialization of the number of clusters (K) using modified ACS before recognition increases tracing ROI’s scalability even for symmetrical features in various plants. Besides, convolutional neural network (CNN)-based PLD recognition models achieve adequate accuracy to some extent. However, memory requirements (large-scaled parameters) and the high computational cost of CNN-based PLD models are burning issues for the memory restricted mobile and IoT-based devices. Therefore, after tracing ROIs, three proposed depth-wise separable convolutional PLD (DSCPLD) models, such as segmented modified DSCPLD (S-modified MobileNet), segmented reduced DSCPLD (S-reduced MobileNet), and segmented extended DSCPLD (S-extended MobileNet), are utilized to represent the constructive trade-off among accuracy, model size, and computational latency. Moreover, we have compared our proposed DSCPLD recognition models with state-of-the-art models, such as MobileNet, VGG16, VGG19, and AlexNet. Among segmented-based DSCPLD models, S-modified MobileNet achieves the best accuracy of 99.55% and F1-sore of 97.07%. Besides, we have simulated our DSCPLD models using both full plant leaf images and segmented plant leaf images and conclude that, after using modified ACS, all models increase their accuracy and F1-score. Furthermore, a new plant leaf dataset containing 6580 images of eight plants was used to experiment with several depth-wise separable convolution models. |
| first_indexed | 2024-03-10T13:03:04Z |
| format | Article |
| id | doaj.art-9445b789d481439ea14cc458b4fa7b94 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-10T13:03:04Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-9445b789d481439ea14cc458b4fa7b942023-11-21T11:22:27ZengMDPI AGSymmetry2073-89942021-03-0113351110.3390/sym13030511Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based ModelsSyed Mohammad Minhaz Hossain0Kaushik Deb1Pranab Kumar Dhar2Takeshi Koshiba3Department of Computer Science & Engineering, Chittagong University of Engineering & Technology (CUET), Chattogram 4349, BangladeshDepartment of Computer Science & Engineering, Chittagong University of Engineering & Technology (CUET), Chattogram 4349, BangladeshDepartment of Computer Science & Engineering, Chittagong University of Engineering & Technology (CUET), Chattogram 4349, BangladeshFaculty of Education and Integrated Arts and Sciences, Waseda University, 1-6-1 Nishiwaseda, Shinjuku-ku, Tokyo 169-8050, JapanProper plant leaf disease (PLD) detection is challenging in complex backgrounds and under different capture conditions. For this reason, initially, modified adaptive centroid-based segmentation (ACS) is used to trace the proper region of interest (ROI). Automatic initialization of the number of clusters (K) using modified ACS before recognition increases tracing ROI’s scalability even for symmetrical features in various plants. Besides, convolutional neural network (CNN)-based PLD recognition models achieve adequate accuracy to some extent. However, memory requirements (large-scaled parameters) and the high computational cost of CNN-based PLD models are burning issues for the memory restricted mobile and IoT-based devices. Therefore, after tracing ROIs, three proposed depth-wise separable convolutional PLD (DSCPLD) models, such as segmented modified DSCPLD (S-modified MobileNet), segmented reduced DSCPLD (S-reduced MobileNet), and segmented extended DSCPLD (S-extended MobileNet), are utilized to represent the constructive trade-off among accuracy, model size, and computational latency. Moreover, we have compared our proposed DSCPLD recognition models with state-of-the-art models, such as MobileNet, VGG16, VGG19, and AlexNet. Among segmented-based DSCPLD models, S-modified MobileNet achieves the best accuracy of 99.55% and F1-sore of 97.07%. Besides, we have simulated our DSCPLD models using both full plant leaf images and segmented plant leaf images and conclude that, after using modified ACS, all models increase their accuracy and F1-score. Furthermore, a new plant leaf dataset containing 6580 images of eight plants was used to experiment with several depth-wise separable convolution models.https://www.mdpi.com/2073-8994/13/3/511plant leaf diseasedepth-wise separable convolutionmodified adaptive centroid-based segmentationcomputational latencymodel size |
| spellingShingle | Syed Mohammad Minhaz Hossain Kaushik Deb Pranab Kumar Dhar Takeshi Koshiba Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models Symmetry plant leaf disease depth-wise separable convolution modified adaptive centroid-based segmentation computational latency model size |
| title | Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models |
| title_full | Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models |
| title_fullStr | Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models |
| title_full_unstemmed | Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models |
| title_short | Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models |
| title_sort | plant leaf disease recognition using depth wise separable convolution based models |
| topic | plant leaf disease depth-wise separable convolution modified adaptive centroid-based segmentation computational latency model size |
| url | https://www.mdpi.com/2073-8994/13/3/511 |
| work_keys_str_mv | AT syedmohammadminhazhossain plantleafdiseaserecognitionusingdepthwiseseparableconvolutionbasedmodels AT kaushikdeb plantleafdiseaserecognitionusingdepthwiseseparableconvolutionbasedmodels AT pranabkumardhar plantleafdiseaserecognitionusingdepthwiseseparableconvolutionbasedmodels AT takeshikoshiba plantleafdiseaserecognitionusingdepthwiseseparableconvolutionbasedmodels |