Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection
Vegetable and fruit plants facilitate around 7.5 billion people around the globe, playing a crucial role in sustaining life on the planet. The rapid increase in the use of chemicals such as fungicides and bactericides to curtail plant diseases is causing negative effects on the agro-ecosystem. The h...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/8812019 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832560015300362240 |
|---|---|
| author | Iftikhar Ahmad Muhammad Hamid Suhail Yousaf Syed Tanveer Shah Muhammad Ovais Ahmad |
| author_facet | Iftikhar Ahmad Muhammad Hamid Suhail Yousaf Syed Tanveer Shah Muhammad Ovais Ahmad |
| author_sort | Iftikhar Ahmad |
| collection | DOAJ |
| description | Vegetable and fruit plants facilitate around 7.5 billion people around the globe, playing a crucial role in sustaining life on the planet. The rapid increase in the use of chemicals such as fungicides and bactericides to curtail plant diseases is causing negative effects on the agro-ecosystem. The high scale prevalence of diseases in crops affects the production quantity and quality. Solving the problem of early identification/diagnosis of diseases by exploiting a quick and consistent reliable method will benefit the farmers. In this context, our research work focuses on classification and identification of tomato leaf diseases using convolutional neural network (CNN) techniques. We consider four CNN architectures, namely, VGG-16, VGG-19, ResNet, and Inception V3, and use feature extraction and parameter-tuning to identify and classify tomato leaf diseases. We test the underlying models on two datasets, a laboratory-based dataset and self-collected data from the field. We observe that all architectures perform better on the laboratory-based dataset than on field-based data, with performance on various metrics showing variance in the range 10%–15%. Inception V3 is identified as the best performing algorithm on both datasets. |
| format | Article |
| id | doaj-art-027a2ab583744698af4d4af9d9583b8f |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-027a2ab583744698af4d4af9d9583b8f2025-02-03T01:28:33ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/88120198812019Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease DetectionIftikhar Ahmad0Muhammad Hamid1Suhail Yousaf2Syed Tanveer Shah3Muhammad Ovais Ahmad4Department of Computer Science and Information Technology, University of Engineering and Technology, Peshawar, 25000, PakistanDepartment of Computer Science and Information Technology, University of Engineering and Technology, Peshawar, 25000, PakistanDepartment of Computer Science and Information Technology, University of Engineering and Technology, Peshawar, 25000, PakistanDepartment of Horticulture, The University of Agriculture, Peshawar, 25000, PakistanDepartment of Mathematics and Computer Science, Karlstad University, Karlstad, 65188, SwedenVegetable and fruit plants facilitate around 7.5 billion people around the globe, playing a crucial role in sustaining life on the planet. The rapid increase in the use of chemicals such as fungicides and bactericides to curtail plant diseases is causing negative effects on the agro-ecosystem. The high scale prevalence of diseases in crops affects the production quantity and quality. Solving the problem of early identification/diagnosis of diseases by exploiting a quick and consistent reliable method will benefit the farmers. In this context, our research work focuses on classification and identification of tomato leaf diseases using convolutional neural network (CNN) techniques. We consider four CNN architectures, namely, VGG-16, VGG-19, ResNet, and Inception V3, and use feature extraction and parameter-tuning to identify and classify tomato leaf diseases. We test the underlying models on two datasets, a laboratory-based dataset and self-collected data from the field. We observe that all architectures perform better on the laboratory-based dataset than on field-based data, with performance on various metrics showing variance in the range 10%–15%. Inception V3 is identified as the best performing algorithm on both datasets.http://dx.doi.org/10.1155/2020/8812019 |
| spellingShingle | Iftikhar Ahmad Muhammad Hamid Suhail Yousaf Syed Tanveer Shah Muhammad Ovais Ahmad Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection Complexity |
| title | Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection |
| title_full | Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection |
| title_fullStr | Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection |
| title_full_unstemmed | Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection |
| title_short | Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection |
| title_sort | optimizing pretrained convolutional neural networks for tomato leaf disease detection |
| url | http://dx.doi.org/10.1155/2020/8812019 |
| work_keys_str_mv | AT iftikharahmad optimizingpretrainedconvolutionalneuralnetworksfortomatoleafdiseasedetection AT muhammadhamid optimizingpretrainedconvolutionalneuralnetworksfortomatoleafdiseasedetection AT suhailyousaf optimizingpretrainedconvolutionalneuralnetworksfortomatoleafdiseasedetection AT syedtanveershah optimizingpretrainedconvolutionalneuralnetworksfortomatoleafdiseasedetection AT muhammadovaisahmad optimizingpretrainedconvolutionalneuralnetworksfortomatoleafdiseasedetection |