A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition
Plant Diseases and Pests are a major challenge in the agriculture sector. An accurate and a faster detection of diseases and pests in plants could help to develop an early treatment technique while substantially reducing economic losses. Recent developments in Deep Neural Networks have allowed resea...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/17/9/2022 |
| _version_ | 1798005848583176192 |
|---|---|
| author | Alvaro Fuentes Sook Yoon Sang Cheol Kim Dong Sun Park |
| author_facet | Alvaro Fuentes Sook Yoon Sang Cheol Kim Dong Sun Park |
| author_sort | Alvaro Fuentes |
| collection | DOAJ |
| description | Plant Diseases and Pests are a major challenge in the agriculture sector. An accurate and a faster detection of diseases and pests in plants could help to develop an early treatment technique while substantially reducing economic losses. Recent developments in Deep Neural Networks have allowed researchers to drastically improve the accuracy of object detection and recognition systems. In this paper, we present a deep-learning-based approach to detect diseases and pests in tomato plants using images captured in-place by camera devices with various resolutions. Our goal is to find the more suitable deep-learning architecture for our task. Therefore, we consider three main families of detectors: Faster Region-based Convolutional Neural Network (Faster R-CNN), Region-based Fully Convolutional Network (R-FCN), and Single Shot Multibox Detector (SSD), which for the purpose of this work are called “deep learning meta-architectures”. We combine each of these meta-architectures with “deep feature extractors” such as VGG net and Residual Network (ResNet). We demonstrate the performance of deep meta-architectures and feature extractors, and additionally propose a method for local and global class annotation and data augmentation to increase the accuracy and reduce the number of false positives during training. We train and test our systems end-to-end on our large Tomato Diseases and Pests Dataset, which contains challenging images with diseases and pests, including several inter- and extra-class variations, such as infection status and location in the plant. Experimental results show that our proposed system can effectively recognize nine different types of diseases and pests, with the ability to deal with complex scenarios from a plant’s surrounding area. |
| first_indexed | 2024-04-11T12:45:30Z |
| format | Article |
| id | doaj.art-c120bc97bd214e76bb4f735e6e63a351 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T12:45:30Z |
| publishDate | 2017-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c120bc97bd214e76bb4f735e6e63a3512022-12-22T04:23:21ZengMDPI AGSensors1424-82202017-09-01179202210.3390/s17092022s17092022A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests RecognitionAlvaro Fuentes0Sook Yoon1Sang Cheol Kim2Dong Sun Park3Department of Electronics Engineering, Chonbuk National University, Jeonbuk 54896, KoreaResearch Institute of Realistic Media and Technology, Mokpo National University, Jeonnam 534-729, KoreaNational Institute of Agricultural Sciences, Suwon 441-707, KoreaIT Convergence Research Center, Chonbuk National University, Jeonbuk 54896, KoreaPlant Diseases and Pests are a major challenge in the agriculture sector. An accurate and a faster detection of diseases and pests in plants could help to develop an early treatment technique while substantially reducing economic losses. Recent developments in Deep Neural Networks have allowed researchers to drastically improve the accuracy of object detection and recognition systems. In this paper, we present a deep-learning-based approach to detect diseases and pests in tomato plants using images captured in-place by camera devices with various resolutions. Our goal is to find the more suitable deep-learning architecture for our task. Therefore, we consider three main families of detectors: Faster Region-based Convolutional Neural Network (Faster R-CNN), Region-based Fully Convolutional Network (R-FCN), and Single Shot Multibox Detector (SSD), which for the purpose of this work are called “deep learning meta-architectures”. We combine each of these meta-architectures with “deep feature extractors” such as VGG net and Residual Network (ResNet). We demonstrate the performance of deep meta-architectures and feature extractors, and additionally propose a method for local and global class annotation and data augmentation to increase the accuracy and reduce the number of false positives during training. We train and test our systems end-to-end on our large Tomato Diseases and Pests Dataset, which contains challenging images with diseases and pests, including several inter- and extra-class variations, such as infection status and location in the plant. Experimental results show that our proposed system can effectively recognize nine different types of diseases and pests, with the ability to deal with complex scenarios from a plant’s surrounding area.https://www.mdpi.com/1424-8220/17/9/2022plant diseasepestdeep convolutional neural networksreal-time processingdetection |
| spellingShingle | Alvaro Fuentes Sook Yoon Sang Cheol Kim Dong Sun Park A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition Sensors plant disease pest deep convolutional neural networks real-time processing detection |
| title | A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition |
| title_full | A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition |
| title_fullStr | A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition |
| title_full_unstemmed | A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition |
| title_short | A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition |
| title_sort | robust deep learning based detector for real time tomato plant diseases and pests recognition |
| topic | plant disease pest deep convolutional neural networks real-time processing detection |
| url | https://www.mdpi.com/1424-8220/17/9/2022 |
| work_keys_str_mv | AT alvarofuentes arobustdeeplearningbaseddetectorforrealtimetomatoplantdiseasesandpestsrecognition AT sookyoon arobustdeeplearningbaseddetectorforrealtimetomatoplantdiseasesandpestsrecognition AT sangcheolkim arobustdeeplearningbaseddetectorforrealtimetomatoplantdiseasesandpestsrecognition AT dongsunpark arobustdeeplearningbaseddetectorforrealtimetomatoplantdiseasesandpestsrecognition AT alvarofuentes robustdeeplearningbaseddetectorforrealtimetomatoplantdiseasesandpestsrecognition AT sookyoon robustdeeplearningbaseddetectorforrealtimetomatoplantdiseasesandpestsrecognition AT sangcheolkim robustdeeplearningbaseddetectorforrealtimetomatoplantdiseasesandpestsrecognition AT dongsunpark robustdeeplearningbaseddetectorforrealtimetomatoplantdiseasesandpestsrecognition |