Standard area diagrams for assessment of powdery mildew severity on tomato leaves and leaflets

Lage, D. A. C.; Marouelli, W. A.; Duarte, Henrique da Silva Silveira; Filho, Adalberto Corrêa Café

doi:10.1016/j.cropro.2014.09.014

Cited by 24 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using image acquisition for determining these areas have proven a reliable method in other cases, but to our knowledge it has not been considered in combination with UV-C when evaluating this radiation effects over the tomato crops themselves and over the powdery mildew infecting the leaflets. One of the advantages of the digital determination of these areas is that no need for any sort of diagram development like SADs has to be made [32], in our case no comparison against this kind of reference is needed, actually as in other works [32], these measurements are considered as reference. We compared the areas measured digitally with those made manually with a caliper and assuming a round shaped lesion, fact that is a reasonable approximation, but measurements of total area of the leaflet using this manual method can be more tedious and less accurate if any geometrical shape easy to estimate the area is used.…”

Section: Discussionmentioning

confidence: 99%

“…These visual disease assessments rely on estimates of percent of leaf area covered by lesions. One typical strategy to increase accuracy and reliability from raters when assessing severity of damage is the use of standard area diagrams (SADs) [31][32][33][34]. These SADs have to be developed for each disease and they help raters to compare and evaluate the problems using SADs as scale of reference.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using UV-C radiation and image analysis for fungus control in tomato plants

Valencia¹,

Patiño²,

Herrera-Ramírez³

et al. 2017

Opt. Pura Apl.

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Using UV-C radiation and image analysis for fungus control in tomato plants

Valencia¹,

Patiño²,

Herrera-Ramírez³

et al. 2017

Opt. Pura Apl.

View full text Add to dashboard Cite

“…The overestimation (positive values of u ) of severity by raters is very well documented in the literature (Andrade et al., 2019; Costa Lage, Marouelli, Duarte, & Café‐Filho, 2015; Rios et al., 2013; Santos & Spósito, 2018). Underestimation (negative values of u ) is also reported (Gomes, Michereff, & Mariano, 2004; Michereff, Maffia, & Noronha, 2000).…”

Section: Discussionmentioning

confidence: 64%

Standard area diagrams to assess scab severity of entire‐margined leaves of sour passion fruit

Brás

Rios

Silva

et al. 2020

Journal of Phytopathology

View full text Add to dashboard Cite

Scab caused by the Cladosporium cladosporioides complex is one of the most important diseases affecting passion fruit yield and fruit quality. Standard area diagrams are useful tools to improve the accuracy and reliability of the estimates of disease severity in many pathosystems. The interpretation of the accuracy of the resulting disease data may be the basis for providing better disease management. This study aimed to develop and validate standard area diagrams (SADs) to quantify scab severity of entire‐margined leaves of sour passion fruit plants. The SADs are composed of ten images of scab severity values (0.4%, 3.5%, 5.4%, 8.0%, 11.1%, 16.2%, 26.1%, 38.2%, 47.9% and 58.9%). Twenty raters (ten experienced and ten inexperienced ones) evaluated the SADs. The raters estimated the same set of fifty images twice. In the examination, the SADs were used, while in the second examination, they were not used. Accuracy was significantly improved by using the SADs. The coefficients of bias (Cb) were 0.96 and 0.98 for the experienced raters and 0.75 and 0.98 for the inexperienced raters without and with SADs, respectively. The correlation coefficient (r) values were 0.95 and 0.97 for the experienced raters and 0.89 and 0.97 for the inexperienced raters without and with the use of the SADs, respectively. Lin's concordance correlation coefficient (ρc) values were 0.91 and 0.95 for the experienced raters and 0.66 and 0.95 for the inexperienced raters without and with the use of the SADs, respectively. Moreover, the coefficient of determination (R2) significantly improved when the SADs were used. The SADs proposed in this study, if properly used, may improve both the accuracy and reliability during the evaluation of scab severity of entire‐margined leaves of sour passion fruit plants.

show abstract

“…Assistive technologies include SADs, image analysis software, and smartphone apps. SADs, also known as diagrammatic keys or diagrammatic scales, were developed to calibrate the human eye to assess the severity of the particular disease symptomatology under evaluation [44][45][46][47]. The use of SADs aims to improve accuracy and reliability, as well as to overcome subjectivity associated with traditional, unaided visual assessment techniques.…”

Section: Leaf-scale Stress Phenotypingmentioning

confidence: 99%

“…A robust SAD should be applicable even under a wide range of environmental conditions and encompass the range of severity values that would be encountered in the field [51]. Before a SAD can be recommended as a tool for severity ratings, it must be quantitatively evaluated for accuracy and precision, and any bias the SAD may cause in ratings [45]. Over the past century these pictorial diagrams, each depicting a range of distinct disease severities on individual plant parts, have been used in phytopathological studies as reference guides focused on individual plant parts such as leaves or leaflets, heads of wheat, or fruit [52][53][54].…”

Section: Leaf-scale Stress Phenotypingmentioning

confidence: 99%

Challenges and Opportunities in Machine-Augmented Plant Stress Phenotyping

Singh

Jones

Ganapathysubramanian

et al. 2021

Trends in Plant Science

150

108

View full text Add to dashboard Cite

Plant stress phenotyping is essential to select stress-resistant varieties and develop better stress-management strategies. Standardization of visual assessments and deployment of imaging techniques have improved the accuracy and reliability of stress assessment in comparison with unaided visual measurement. The growing capabilities of machine learning (ML) methods in conjunction with image-based phenotyping can extract new insights from curated, annotated, and high-dimensional datasets across varied crops and stresses. We propose an overarching strategy for utilizing ML techniques that methodically enables the application of plant stress phenotyping at multiple scales across different types of stresses, program goals, and environments. Understanding Plant Stress Is Crucial for Yield ProtectionPlant stress is a state of plant growth under non-ideal environmental conditions caused by various biotic (pathogen, insect, pest, and weed) and abiotic (temperature stress, nutrient deficiency, toxicity, herbicide) factors. Significant crop yield loss due to various plant stresses has the potential to threaten global food security [1]. Plant disease epidemics are a constant threat and continue to emerge owing to complex host-pathogen-environment dynamics [2,3]. Global climate change can exacerbate this situation because of the predicted increases in insect and pathogen pressure for major grains including rice (Oryza sativa), maize (Zea mays L.), and wheat (Triticum aestivum) [4]. Moreover, weather-related challenges such as drought, flooding, hail, and windstorms adversely affect crop production. Yield preservation and protection is a dynamic challenge for pathologists, entomologists, plant breeders, and crop producers globally. Understanding plant stress is crucial for improving yield protection to meet with the growing demand for food production [5]. In the past decade, significant advances in image processing and machine learning (ML; see Glossary) algorithms have been made to handle image-based stress datasets for automated data analysis and application of trained models [6][7][8]. We review the development and application of ML algorithms for image-based plant stress phenotyping at multiple scales ranging from leaf and canopy (plot) to field (production) scale. We discuss some of the major challenges in the practical application of ML algorithms, and list future efforts that will be necessary to make ML a more mainstream tool in plant stress phenotyping applications and usage. HighlightsPlant stress phenotyping is challenging to implement at multiple organizational scales (leaf, canopy, field).There is a need to improve the speed, accuracy, reliability, and scalability of stress phenotyping while allowing flexibility for highly variable program goals.

show abstract

Standard area diagrams for assessment of powdery mildew severity on tomato leaves and leaflets

Cited by 24 publications

References 33 publications

Using UV-C radiation and image analysis for fungus control in tomato plants

Using UV-C radiation and image analysis for fungus control in tomato plants

Standard area diagrams to assess scab severity of entire‐margined leaves of sour passion fruit

Challenges and Opportunities in Machine-Augmented Plant Stress Phenotyping

Contact Info

Product

Resources

About