1
|
Huang Q, Wu X, Wang Q, Dong X, Qin Y, Wu X, Gao Y, Hao G. Knowledge Distillation Facilitates the Lightweight and Efficient Plant Diseases Detection Model. PLANT PHENOMICS (WASHINGTON, D.C.) 2023; 5:0062. [PMID: 37396495 PMCID: PMC10308957 DOI: 10.34133/plantphenomics.0062] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/14/2022] [Accepted: 06/06/2023] [Indexed: 07/04/2023]
Abstract
Plant disease diagnosis in time can inhibit the spread of the disease and prevent a large-scale drop in production, which benefits food production. Object detection-based plant disease diagnosis methods have attracted widespread attention due to their accuracy in classifying and locating diseases. However, existing methods are still limited to single crop disease diagnosis. More importantly, the existing model has a large number of parameters, which is not conducive to deploying it to agricultural mobile devices. Nonetheless, reducing the number of model parameters tends to cause a decrease in model accuracy. To solve these problems, we propose a plant disease detection method based on knowledge distillation to achieve a lightweight and efficient diagnosis of multiple diseases across multiple crops. In detail, we design 2 strategies to build 4 different lightweight models as student models: the YOLOR-Light-v1, YOLOR-Light-v2, Mobile-YOLOR-v1, and Mobile-YOLOR-v2 models, and adopt the YOLOR model as the teacher model. We develop a multistage knowledge distillation method to improve lightweight model performance, achieving 60.4% mAP@ .5 in the PlantDoc dataset with small model parameters, outperforming existing methods. Overall, the multistage knowledge distillation technique can make the model lighter while maintaining high accuracy. Not only that, the technique can be extended to other tasks, such as image classification and image segmentation, to obtain automated plant disease diagnostic models with a wider range of lightweight applicability in smart agriculture. Our code is available at https://github.com/QDH/MSKD.
Collapse
Affiliation(s)
- Qianding Huang
- State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
| | - Xingcai Wu
- State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
| | - Qi Wang
- State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
- Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry, Guizhou University, Guiyang 550025, China
| | - Xinyu Dong
- State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
| | - Yongbin Qin
- Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry, Guizhou University, Guiyang 550025, China
| | - Xue Wu
- State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
- National Key Laboratory of Green Pesticide, Guizhou University, Guiyang 550025, China
| | - Yangyang Gao
- National Key Laboratory of Green Pesticide, Guizhou University, Guiyang 550025, China
| | - Gefei Hao
- State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
- National Key Laboratory of Green Pesticide, Guizhou University, Guiyang 550025, China
| |
Collapse
|
2
|
Heineck GC, Casanova J, Porter LD. Suitable Methods of Inoculation and Quantification of Fusarium Root Rot in Lentil. PLANT DISEASE 2023:PDIS07221658RE. [PMID: 36265151 DOI: 10.1094/pdis-07-22-1658-re] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/05/2023]
Abstract
Lentil (Lens culinaris L. subsp. culinaris) is an important grain legume grown worldwide. As its popularity grows among consumers and more acres are produced, new root rot complexes have become more prevalent. This work sought to develop methods for studying root rot caused by Fusarium avenaceum in lentil using controlled environments. The objectives were to (i) find an effective and seed-safe sterilization technique, (ii) optimize the inoculation technique and lentil growing environment, and (iii) develop visual and automated disease scoring systems. Results showed the use of detergent and a low concentration (0.1%) of NaClO (the active ingredient in bleach) maintained germinability and effectively eliminated bacterial and fungal contamination on seeds. Other treatments, such as ethanol, reduced seed germination or failed to kill pathogenic fungi such as Fusarium spp. Placing inoculum at a moderate rate of 1 × 106 spores both directly on the seed and on top of the media covering the seed improved severity scores and reduced escapes compared with placement on top of the media only. Visual severity scoring systems and diagrammatic scales were developed for scoring the cotyledon region and roots. A computer vision algorithm was designed to improve the efficiency of scoring the cotyledon region and roots for disease severity using a simple RGB camera and lightbox. Visual and computer scores were best correlated when images were visually scored on a monitor, and multiple images were averaged. The scores generated from the computer vision algorithm had better correlations with visual scores for cotyledon rot (r = 0.92 and β1 = 0.96) than root rot (r = 0.62 and β1 = 0.67).
Collapse
Affiliation(s)
- G C Heineck
- USDA-ARS Northwest Sustainable Agroecosystems Research Unit, Washington State University, Prosser, WA 99350
| | - Joaquin Casanova
- USDA-ARS Northwest Sustainable Agroecosystems Research Unit, Washington State University, Pullman, WA 99164
| | - Lyndon D Porter
- USDA-ARS Grain Legume Genetics and Physiology Research Unit, Prosser, WA 99350
| |
Collapse
|
3
|
Jackulin C, Murugavalli S, Valarmathi K. RIFATA: Remora improved invasive feedback artificial tree algorithm-enabled hybrid deep learning approach for root disease classification. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2023.104578] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/24/2023]
|
4
|
Zaji A, Liu Z, Xiao G, Sangha JS, Ruan Y. A survey on deep learning applications in wheat phenotyping. Appl Soft Comput 2022. [DOI: 10.1016/j.asoc.2022.109761] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
5
|
Divyanth LG, Marzougui A, González-Bernal MJ, McGee RJ, Rubiales D, Sankaran S. Evaluation of Effective Class-Balancing Techniques for CNN-Based Assessment of Aphanomyces Root Rot Resistance in Pea ( Pisum sativum L.). SENSORS (BASEL, SWITZERLAND) 2022; 22:7237. [PMID: 36236336 PMCID: PMC9572822 DOI: 10.3390/s22197237] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/26/2022] [Revised: 09/15/2022] [Accepted: 09/16/2022] [Indexed: 06/16/2023]
Abstract
Aphanomyces root rot (ARR) is a devastating disease that affects the production of pea. The plants are prone to infection at any growth stage, and there are no chemical or cultural controls. Thus, the development of resistant pea cultivars is important. Phenomics technologies to support the selection of resistant cultivars through phenotyping can be valuable. One such approach is to couple imaging technologies with deep learning algorithms that are considered efficient for the assessment of disease resistance across a large number of plant genotypes. In this study, the resistance to ARR was evaluated through a CNN-based assessment of pea root images. The proposed model, DeepARRNet, was designed to classify the pea root images into three classes based on ARR severity scores, namely, resistant, intermediate, and susceptible classes. The dataset consisted of 1581 pea root images with a skewed distribution. Hence, three effective data-balancing techniques were identified to solve the prevalent problem of unbalanced datasets. Random oversampling with image transformations, generative adversarial network (GAN)-based image synthesis, and loss function with class-weighted ratio were implemented during the training process. The result indicated that the classification F1-score was 0.92 ± 0.03 when GAN-synthesized images were added, 0.91 ± 0.04 for random resampling, and 0.88 ± 0.05 when class-weighted loss function was implemented, which was higher than when an unbalanced dataset without these techniques were used (0.83 ± 0.03). The systematic approaches evaluated in this study can be applied to other image-based phenotyping datasets, which can aid the development of deep-learning models with improved performance.
Collapse
Affiliation(s)
- L. G. Divyanth
- Department of Biological Systems Engineering, Washington State University, Pullman, WA 99164, USA
- Department of Agricultural and Food Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721302, India
| | - Afef Marzougui
- Department of Biological Systems Engineering, Washington State University, Pullman, WA 99164, USA
| | | | - Rebecca J. McGee
- Grain Legume Genetics and Physiology Research Unit, US Department of Agriculture-Agricultural Research Service (USDA-ARS), Pullman, WA 99164, USA
| | - Diego Rubiales
- The Institute for Sustainable Agriculture, Spanish National Research Council, 14001 Cordova, Spain
| | - Sindhuja Sankaran
- Department of Biological Systems Engineering, Washington State University, Pullman, WA 99164, USA
| |
Collapse
|
6
|
Analysis of RGB Plant Images to Identify Root Rot Disease in Korean Ginseng Plants Using Deep Learning. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12052489] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Ginseng is an important medicinal plant in Korea. The roots of the ginseng plant have medicinal properties; thus, it is very important to maintain the quality of ginseng roots. Root rot disease is a major disease that affects the quality of ginseng roots. It is important to predict this disease before it causes severe damage to the plants. Hence, there is a need for a non-destructive method to identify root rot disease in ginseng plants. In this paper, a method to identify the root rot disease by analyzing the RGB plant images using image processing and deep learning is proposed. Initially, plant segmentation is performed, and then the noise regions are removed in the plant images. These images are given as input to the proposed linear deep learning model to identify root rot disease in ginseng plants. Transfer learning models are also applied to these images. The performance of the proposed method is promising in identifying root rot disease.
Collapse
|
7
|
Xia F, Xie X, Wang Z, Jin S, Yan K, Ji Z. A Novel Computational Framework for Precision Diagnosis and Subtype Discovery of Plant With Lesion. FRONTIERS IN PLANT SCIENCE 2022; 12:789630. [PMID: 35046977 PMCID: PMC8761810 DOI: 10.3389/fpls.2021.789630] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/05/2021] [Accepted: 11/03/2021] [Indexed: 05/14/2023]
Abstract
Plants are often attacked by various pathogens during their growth, which may cause environmental pollution, food shortages, or economic losses in a certain area. Integration of high throughput phenomics data and computer vision (CV) provides a great opportunity to realize plant disease diagnosis in the early stage and uncover the subtype or stage patterns in the disease progression. In this study, we proposed a novel computational framework for plant disease identification and subtype discovery through a deep-embedding image-clustering strategy, Weighted Distance Metric and the t-stochastic neighbor embedding algorithm (WDM-tSNE). To verify the effectiveness, we applied our method on four public datasets of images. The results demonstrated that the newly developed tool is capable of identifying the plant disease and further uncover the underlying subtypes associated with pathogenic resistance. In summary, the current framework provides great clustering performance for the root or leave images of diseased plants with pronounced disease spots or symptoms.
Collapse
Affiliation(s)
- Fei Xia
- College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, China
| | - Xiaojun Xie
- College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, China
- Center for Data Science and Intelligent Computing, Nanjing Agricultural University, Nanjing, China
| | - Zongqin Wang
- College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, China
| | - Shichao Jin
- Plant Phenomics Research Centre, Academy for Advanced Interdisciplinary Studies, Regional Technique Innovation Center for Wheat Production, Key Laboratory of Crop Physiology and Ecology in Southern China, Ministry of Agriculture, Nanjing Agricultural University, Nanjing, China
- Collaborative Innovation Centre for Modern Crop Production co-sponsored by Province and Ministry, Jiangsu Key Laboratory for Information Agriculture, Nanjing Agricultural University, Nanjing, China
| | - Ke Yan
- Department of Building, School of Design and Environment, National University of Singapore, Singapore, Singapore
| | - Zhiwei Ji
- College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, China
- Center for Data Science and Intelligent Computing, Nanjing Agricultural University, Nanjing, China
| |
Collapse
|