Skip to main content
SpringerLink
Log in

Determination of the severity of Septoria leaf spot in tomato by using digital images

  • Original Paper
  • Published:
Australasian Plant Pathology Aims and scope Submit manuscript

Abstract

The aim of this study is to determine the severity of the disease Septoria leaf spot in tomato plants, through computational analysis of digital images of leaves affected. We collected and obtained digital images of tomato leaves with absence and presence of the disease with varying degrees of severity. From a script written in R with the EBImage package, the image was decomposed into three levels of color (RGB) and, through the process of thresholding the image segmentation, was performed separating sheet and injuries in relation to the background, determining the percentage of damaged area. Statistical properties were extracted from the original images and, from them and the severity quantified by software, was realized the process of correlation and regression analysis to indicate a template that determines the percentage of damaged area through the properties of the images. Subsequently, these models were tested, with a new image bank, from the RMSE error measures. The methodology described, was able to identify and quantify the damaged areas of the leaves with symptoms of diseases, extract the statistical properties of the images as allowed to predict mathematical models with acceptable potential and quality for indirect determination of the percentage of injured area through the properties of the images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  • Agrios GN (2005) Plant pathology, 5th edn. Elsevier Academic Press, Burlington, 922 p

    Google Scholar 

  • Ali H, Lali MI, Nawaz MZ, Sharif M, Saleem BA (2017) Symptom based automated detection of citrus diseases using color histogram and textural descriptors. Comput Electron Agric 138:92–104

    Article  Google Scholar 

  • Amorim L, Rezende JAM, Bergamim Filho A, Camargo FA (2016) Manual de Fitopatologia: Doenças das Plantas Cultivadas. 5th Ouro Fino-MG, Agronômica Ceres Ltda

  • Amorim L, Rezende JAM, Bergamim Filho A (2018) Manual de Fitopatologia: Princípios e Conceitos, vol v. 1, 5th edn. Agronomica Ceres Ltda, OuroFino-MG, 573 p

    Google Scholar 

  • Barbedo JGA (2014) An automatic method to detect and measure leaf disease symptoms using digital image processing. Plant Dis 98(12):1709–1716

    Article  Google Scholar 

  • Barbedo JGA (2016) A review on the main challenges in automatic plant disease identification based on visible range images. Biosyst Eng 144:52–60

    Article  Google Scholar 

  • Barbedo JGA, Koenigkan LV, Santos TT (2016) Identifying multiple plant diseases using digital image processing. Biosyst Eng 147:104–116

    Article  Google Scholar 

  • Bock CH, Poole GH, Parker PE, Gottwald TR (2010) Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging. Crit Rev Plant Sci 29:59–107

    Article  Google Scholar 

  • Camargo A, Smith JS (2009) An image-processing based algorithm to automatically identify plant disease visual symptoms. Biosyst Eng 102:9–21

    Article  Google Scholar 

  • Conci A, Azevedo E, Leta EFR (2008) Computação Gráfica: Processamento e Análise de Imagens Digitais, v. 2 Campus/Elsevier, 528 p

  • Duarte LT, Lobo Junior M, Cortes MVCB (2013) Recomendações para Coleta e Envio de Material ao Laboratório de Fitopatologia para Diagnóstico de Doenças em Plantas. Documentos, Embrapa Arroz e Feijão, 20 p

  • Emiliano PC (2013) Critérios de informação: como eles se comportam em diferentes modelos. UFLA, Lavras, 193 p

    Google Scholar 

  • Gauchi JP, Chagnon P (2001) Comparison of selection methods of explanatory variables in PLS regression with application to manufacturing process data. Chemom Intell Lab Syst 58:171–193

    Article  CAS  Google Scholar 

  • Gujarati DN (2006) Econometria básica, 4th edn. Elsevier, Oxford

  • Hamuda E, Glavin M, Jones E (2016) Um levantamento de técnicas de processamento de imagens para extração e segmentação de plantas no campo. Comput Electron Agric 125:184–199

    Article  Google Scholar 

  • Heineck GC, McNish IG, Jungers JM, Gilbert E, Watkins E (2019) Using R-based image analysis to quantify rusts on perennial ryegrass. Plant Phenome J 2:180010

    Article  Google Scholar 

  • Ihaka R, Gentleman R (1996) R: A Language for Data Analysis and Graphics. Journal of Computational and Graphical Statistics 5(3):299-314

  • Iqbala Z, Khana MAB, Sharifa M, Shaha JH, Rehmana MHU, Javedc K (2018) An automated detection and classification of citrus plant diseases using image processing techniques: a review. Comput Electron Agric 153:12–32

    Article  Google Scholar 

  • Kruse OMO, Prats-Montalbán JM, Indahl UG, KvaalK FA, Futsaether CM (2014) Pixel classification methods for identifying and quantifying leaf surface injury from digital images. Comput Electron Agric 108:155–165

    Article  Google Scholar 

  • Madden LV, Hughes G, Van Den Bosch F (2007) The study of plant disease epidemics. APS Press, St Paul, 432 p

    Google Scholar 

  • Marques Filho O, Vieira Neto H (1999) Processamento Digital de Imagens. Brasport, Rio de Janeiro, 307 p

    Google Scholar 

  • Moreira A (2011) Métodos para segmentação binária para imagens em tons de cinza. LFNATEC, Londrina, 28 p

    Google Scholar 

  • Nutter FW Jr, Esker PD (2006) The role of psychophysics in phytopathology: the weber–Fechner law revisited. Eur J Plant Pathol 114:199–213

    Article  Google Scholar 

  • Otsu N (1979) A threshold selection method from gray-level histograms. Automatica 11:23–27

    Google Scholar 

  • Pau G, Fuchs F, Sklyar O, Boutros M, Huber W (2010) EBImage—an R package for image processing with applications to cellular phenotypes. Bioinformatics 26(7):979–981

    Article  CAS  Google Scholar 

  • Pedrini H, Schwartz WR (2008) Análise de imagens digitais: Princípios, Algoritmos e Aplicações. Thomson Learning, São Paulo, 508 p

    Google Scholar 

  • Price TV, Gross R, Ho Wey J, Osborne CF (1993) A comparison of visual and digital image-processing methods in quantifying the severity of coffee leaf rust (Hemileia vastatrix). Aust J Exp Agric 33:97–101

    Article  Google Scholar 

  • Reis A, Boiteux LS, Lopes CA (2006) Mancha-de-septória: doença limitante do tomateiro no período de chuvas. Comunicado Técnico, 37 – Embrapa, p.1-6

  • Sengar N, Dutta MK, Travieso CM (2018) Técnica de visão computacional para identificação e quantificação da doença do oídio em folhas de cerejeira. Computing 100:1189–1201

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Federal University of Santa Catarina, Curitibanos Campus, Ulysses Gaboardi Road, Km 3, Curitibanos, SC, 89520-000, Brazil

    Amanda do Prado Mattos, João Batista Tolentino Júnior & Adriana Terumi Itako

Authors
  1. Amanda do Prado Mattos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. João Batista Tolentino Júnior
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Adriana Terumi Itako
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Amanda do Prado Mattos.

Appendices

Appendix 1 – Original images and images segmented by R software in relation to leaf and stain (necrosis + chlorosis) and their percentages of injured area

Fig. 7
figure 7

(11.58%)

Full size image
Fig. 8
figure 8

(5,01%)

Full size image
Fig. 9
figure 9

(21,19%)

Full size image
Fig. 10
figure 10

(35,08%)

Full size image
Fig. 11
figure 11

(7,48%)

Full size image
Fig. 12
figure 12

(0%)

Full size image
Fig. 13
figure 13

(3,62%)

Full size image
Fig. 14
figure 14

(0,16%)

Full size image
Fig. 15
figure 15

(26,10%)

Full size image
Fig. 16
figure 16

(0,92%)

Full size image
Fig. 17
figure 17

(53,69%)

Full size image
Fig. 18
figure 18

(0,51%)

Full size image
Fig. 19
figure 19

(28,17%)

Full size image
Fig. 20
figure 20

(3,11%)

Full size image
Fig. 21
figure 21

(0,48%)

Full size image
Fig. 22
figure 22

(0,34%)

Full size image
Fig. 23
figure 23

(26,63%)

Full size image
Fig. 24
figure 24

(0,46%)

Full size image
Fig. 25
figure 25

(0,10%)

Full size image
Fig. 26
figure 26

(4,56%)

Full size image
Fig. 27
figure 27

(5,62%)

Full size image
Fig. 28
figure 28

(3,81%)

Full size image
Fig. 29
figure 29

(16,98%)

Full size image
Fig. 30
figure 30

(0,08%)

Full size image
Fig. 31
figure 31

(15,03%)

Full size image
Fig. 32
figure 32

(1,13%)

Full size image
Fig. 33
figure 33

(7,30%)

Full size image
Fig. 34
figure 34

(2,16%)

Full size image
Fig. 35
figure 35

(0,04%)

Full size image
Fig. 36
figure 36

(15,62%)

Full size image

Appendix 2 – Script elaborated in R software for quantification of severity

figure a
figure b
figure c

Appendix 3 – Script elaborated in the R software for extracting the statistical properties of the image and correlation process

figure d
figure e
figure f
figure g

Appendix 4 – Key commands used and their functions

BIC :

Calculates the Bayesian information criterion.

channel :

Handles color space conversions between image modes.

computeFeatures.shape :

Calculates morphological and texture characteristics of image objects.

colour :

computes the correlation of x and y if these are vectors. If x and Y are arrays, then the correlation between the X columns and the y columns are computed

display :

Shows the created image.

fillHull :

Fills loopholes in objects.

library :

Loads packages into the software

lm :

Performs regression, analysis of variance and covariance.

mean :

Calculates the average of the indicated values.

otsu :

Returns a threshold value based on the Otsu method, wich can be used to reduce the grayscale image to a binary image.

proc.time :

Determines how long the system (in seconds) takes to run the process.

readImage :

Reads and writes images to/from and URLs.

regsubsets :

Multiple linear regression analysis for choosing a better model.

Resize :

Performs all transformations linears spatial: rotation, translation, resizing e transformation em general.

rm :

Removes specified objects.

sd :

Calculates the standard deviation.

sum :

Returns the sum of all vallues.

write.xlsx :

Saves data to a spread sheet xlsx.

writeTIFF :

Saves one or more bitmap images in the format TIFF.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mattos, A.d., Tolentino Júnior, J.B. & Itako, A.T. Determination of the severity of Septoria leaf spot in tomato by using digital images. Australasian Plant Pathol. 49, 329–356 (2020). https://doi.org/10.1007/s13313-020-00697-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13313-020-00697-6

Keywords

Search

Navigation