Combination of multivariate curve resolution with factorial discriminant analysis for the detection of grapevine diseases using hyperspectral imaging. A case study: flavescence dorée

Garcia, Sílvia Mas; Ryckewaert, Maxime; Abdelghafour, Florent; Metz, Maxime; Moura, Daniel C.; Feilhes, Carole; Prezman, Fanny; Bendoula, Ryad

doi:10.1039/d1an01735g

Cited by 7 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This system has proven to be useful for capturing images with different cameras, e.g., RGB, multi-, and hyperspectral. Integrating these technologies with suitable analytical approaches can make it possible for researchers to differentiate between infected and healthy plants, as well as determine the severity, stage, and type of disease [39,40].…”

Section: Introductionmentioning

confidence: 99%

The Combination of Low-Cost, Red–Green–Blue (RGB) Image Analysis and Machine Learning to Screen for Barley Plant Resistance to Net Blotch

Leiva,

Dhakal,

Himanen

et al. 2024

Plants

View full text Add to dashboard Cite

Challenges of climate change and growth population are exacerbated by noticeable environmental changes, which can increase the range of plant diseases, for instance, net blotch (NB), a foliar disease which significantly decreases barley (Hordeum vulgare L.) grain yield and quality. A resistant germplasm is usually identified through visual observation and the scoring of disease symptoms; however, this is subjective and time-consuming. Thus, automated, non-destructive, and low-cost disease-scoring approaches are highly relevant to barley breeding. This study presents a novel screening method for evaluating NB severity in barley. The proposed method uses an automated RGB imaging system, together with machine learning, to evaluate different symptoms and the severity of NB. The study was performed on three barley cultivars with distinct levels of resistance to NB (resistant, moderately resistant, and susceptible). The tested approach showed mean precision of 99% for various categories of NB severity (chlorotic, necrotic, and fungal lesions, along with leaf tip necrosis). The results demonstrate that the proposed method could be effective in assessing NB from barley leaves and specifying the level of NB severity; this type of information could be pivotal to precise selection for NB resistance in barley breeding.

show abstract

Section: Introductionmentioning

confidence: 99%

The Combination of Low-Cost, Red–Green–Blue (RGB) Image Analysis and Machine Learning to Screen for Barley Plant Resistance to Net Blotch

Leiva,

Dhakal,

Himanen

et al. 2024

Plants

View full text Add to dashboard Cite

show abstract

“…Similarly, morphological analysis of leaves, seeds, and/or tubers (in the case of the root vegetable crops) has proven to be effective for evaluating quality parameters and disease severity for certain bio-aggressors (Wiwart et al, 2001;Tanabata et al, 2012;Whan et al, 2014;Komyshev et al, 2017;Si et al, 2017;Caraza-Harter and Endelman, 2020;Neilson et al, 2021;Miller et al, 2022). Solutions using more complex equipment to capture images in the VIS-NIR domain (multispectral and hyperspectral cameras) have been also proposed to evaluate moisture and nutrient content, plant health, seed water content composition and structure parameters, and vegetation indexes (Garcia et al, 2021;Mortensen et al, 2021;Femenias et al, 2022;Rangarajan et al, 2022;Ryckewaert et al, 2022;Yipeng et al, 2022;Qi et al, 2023;Solgi et al, 2023). However, simpler approaches may produce inconsistent outputs, while more advanced ones are costly and often impractical or unsuitable for use in real-scale trials.…”

Section: Introductionmentioning

confidence: 99%

Developing affordable high-throughput plant phenotyping methods for breeding of cereals and tuber crops

Leiva-Sandoval¹

2023

Acta Universitatis Agriculturae Sueciae

View full text Add to dashboard Cite

High-throughput plant phenotyping (HTPP) is a fast, accurate, and non-destructive process for evaluating plants' health and environmental adaptability. HTPP accelerates the identification of agronomic traits of interest, eliminates subjectivism (which is innate to humans), and facilitates the development of adapted genotypes. Current HTPP methods often rely on imaging sensors and computer vision both in the field and under controlled (indoor) conditions. However, their use is limited by the costs and complexity of the necessary instrumentation, data analysis tools, and software. This issue could be overcome by developing more cost-efficient and user-friendly methods that let breeders, farmers, and stakeholders access the benefits of HTPP. To assist such efforts, this thesis presents an ensemble of dedicated affordable phenotyping methods using RGB imaging for a range of key applications under controlled conditions. The affordable Phenocave imaging system for use in controlled conditions was developed to facilitate studies on the effects of abiotic stresses by gathering data on important plant characteristics related to growth, yield, and adaptation to growing conditions and cultivation systems. Phenocave supports imaging sensors including visible (RGB), spectroscopic (multispectral and hyperspectral), and thermal imaging. Additionally, a pipeline for RGB image analysis was implemented as a plugin for the free and easy-to-use software ImageJ. This plugin has since proven to be an accurate alternative to conventional measurements that produces highly reproducible results. A subsequent study was conducted to evaluate the effects of heat and drought stress on plant growth and grain nutrient composition in wheat, an important staple cereal in Sweden. The effects of stress on plant growth were evaluated using image analysis, while stress-induced changes in the abundance of key plant compounds were evaluated by analyzing the nutrient composition of grains via chromatography. This led to the discovery of genotypes whose harvest quality remains stable under heat and drought stress. The next objective was to evaluate biotic stress; for this case, the effect of the fungal disease Fusarium head blight (FHB) that affects grain development in wheat was investigated. For this purpose, seed phenotyping parameters were used to determine the components and settings of a statistical model, which predicts the occurrence of FHB. The results reveal that grain morphology evaluations, such as length and width, were found to be significantly affected by the disease. Another study was carried out to estimate the disease severity of the common scab (CS) in potatoes, a widely popular food source. CS occurs on the tubers and reduces their visual appeal, significantly affecting their market value. Tubers were analyzed by a deep learning-based method to estimate disease lesion areas caused by CS. Results showed a high correlation between the predictions and expert visual scorings of the disease and proved to be a potential tool for the selection of genotypes that fulfill the market standards and resistance to CS. Both case studies highlight the role of imaging in plant health monitoring and its integration into the larger picture of plant health management. The methods presented in this work are a starting point for bridging the gap between costs and accessibility to imaging technology. These are affordable and user-friendly resources for generating pivotal knowledge on plant development and genotype selection. In the future, image acquisition of all the methods can be integrated into the Phenocave system, potentially allowing for a more automated and efficient plant health monitoring process, leading to the identification of tolerant genotypes to biotic and abiotic stresses.

show abstract

“…Spectroscopy and hyperspectral imaging (HSI), especially in the visible and near infrared (VIS-NIR) domain, are very popular automated and non-destructive techniques for the detection of numerous plant diseases (Mahlein et al, 2018). When these technologies are combined with appropriate analysis and modelling methods, it is possible to discriminate infected plants from healthy ones, to predict infection levels and stages, or even to discriminate between different diseases (Mas Garcia et al, 2021;Lowe et al, 2017;Mahlein et al, 2012;Couture et al, 2013). In addition, spectral data can be used to deduce changes in leaf chemistry or structure (Jacquemoud and Ustin, 2019;Bos and Parlevliet, 1995).…”

Section: Introductionmentioning

confidence: 99%

Including Measurement Effects and Temporal Variations in VIS-NIRS Models to Improve Early Detection of Plant Disease: Application to Alternaria Solani in Potatoes

et al. 2022

View full text Add to dashboard Cite

Combination of multivariate curve resolution with factorial discriminant analysis for the detection of grapevine diseases using hyperspectral imaging. A case study: flavescence dorée

Abstract: A new efficient protocol based on hyperspectral imaging and data analysis tools to detect phytopathologies is demonstrated.

Cited by 7 publications

References 17 publications

The Combination of Low-Cost, Red–Green–Blue (RGB) Image Analysis and Machine Learning to Screen for Barley Plant Resistance to Net Blotch

The Combination of Low-Cost, Red–Green–Blue (RGB) Image Analysis and Machine Learning to Screen for Barley Plant Resistance to Net Blotch

Developing affordable high-throughput plant phenotyping methods for breeding of cereals and tuber crops

Including Measurement Effects and Temporal Variations in VIS-NIRS Models to Improve Early Detection of Plant Disease: Application to Alternaria Solani in Potatoes

Contact Info

Product

Resources

About