Detection of foliar diseases using image processing techniques

This paper presents the development of a methodology to detect the percentage of affected area of Phytophthora infestans disease in tomato plants, using digital image processing techniques to extract the regions of interest with color analysis, where the YIQ and TSL models for the detection of the disease. The method consists of solving one of the most common problems in images that is segmentation, in this case the background and the disease with the Plant Village database, which was captured under uncontrolled lighting conditions. In the experiments conducted, it is observed that our method achieved a performance of 98.60% for the detection of healthy pixels and 98.17% in detection of sick pixels. This process was subjected to comparison against other alternatives of the state of the art like K-means with HSV and LAB, showing a referred error regarding the leaf size of 4.32 ± 5.44% in the detection of the disease and a computational time of 0.03 ± 0.01 [s] in comparison with the other procedures, in addition, this methodology was implemented to detect the foliar diseases black Sigatoka and yellow Sigatoka in banana leaves obtaining satisfactory results.

Keywords:
affected area; black Sigatoka; Phytophthora infestans; yellow Sigatoka.

Authorship

Leidy Esperanza Pamplona Beron

Universidad Tecnológica de Pereira, Facultad de Ingenierías, Pereira, Risaralda, Colombia. lepamplona@utp.edu.co; afcalvo@utp.edu.co; abejarano@utp.edu.coUniversidad Tecnológica de PereiraColombiaPereira, Risaralda, ColombiaUniversidad Tecnológica de Pereira, Facultad de Ingenierías, Pereira, Risaralda, Colombia. lepamplona@utp.edu.co; afcalvo@utp.edu.co; abejarano@utp.edu.co

Andrés Felipe Calvo Salcedo ^**Corresponding author: afcalvo@utp.edu.co

https://orcid.org/0000-0001-9409-8982

Arley Bejarano Martínez

*Corresponding author: afcalvo@utp.edu.co

SCIMAGO INSTITUTIONS RANKINGS

Figures | Tables

Figures (9)
Tables (7)

No.	Healthy Leaf Photo	Quantity Pixel Sheet	Photo Diseased Sick	Quantity Pixel Disease
1	8	21823	53	8680
2	24	29317	55	29244
⋮	⋮	⋮	⋮	⋮
50	713	20465	1204	26158

Methodologies	Healthy [%]	Sick [%]	Average error [%]
1. Proposed method	1.40 ± 3.55	1.93 ± 3.24	1.67 ± 3.40
2. Segmented database	0.79 ± 0.50	0.91 ± 5.80	0.85 ± 3.15
3. Operations in RGB	2.12 ± 2.80	2.02 ± 3.96	2.07 ± 3.38
4. Operations in RGB and HSI	2.51 ± 10.58	3.49 ± 7.13	3.00 ± 8.86

Methodologies	Referred error [%]
1. Proposed method	4.32 ± 5.44
2. K-means with LAB (*Sharma et al., 2017*Sharma R, Singh A, Dutta MK, Riha K & Kriz P (2017) Image processing based automated identification of late blight disease from leaf images of potato crops. In: 40thTelecommunications and Signal Processing, Barcelona. Anais, IEEE. p. 758-762.)	7.72 ± 7.24
3. K-means with HSV	10.36 ± 7.60

Methodologies	Time [s]
1. Proposed method	0.03 ± 0.01
2. K-means with LAB (*Sharma et al., 2017*Sharma R, Singh A, Dutta MK, Riha K & Kriz P (2017) Image processing based automated identification of late blight disease from leaf images of potato crops. In: 40thTelecommunications and Signal Processing, Barcelona. Anais, IEEE. p. 758-762.)	5.15 ± 0.28
3. K-means with HSV	4.91 ± 0.21

Severity level	None	Low	Medium	High
Banana Image Disease detection

RGB	Red (R), Green (G), Blue (B).
HSI	Tone (H), Saturation (S), Intensity (I), (*Gonzalez et al., 2009*Gonzalez RC, Woods RE & Eddins SL (2009) Digital Image Processing Using MATLAB. 2nd ed. Upper Saddle River, Prentice Hall. 609p.).
HSV	Tone (H), Saturation (S), Value that is the brightness (V), (*Gonzalez et al., 2009*Gonzalez RC, Woods RE & Eddins SL (2009) Digital Image Processing Using MATLAB. 2nd ed. Upper Saddle River, Prentice Hall. 609p.).
LAB	Luminance (L), Color range from green to red (A), Color range from blue to yellow (B), *(Gonzalez et al., 2009*Gonzalez RC, Woods RE & Eddins SL (2009) Digital Image Processing Using MATLAB. 2nd ed. Upper Saddle River, Prentice Hall. 609p.).
YCBCR	Luminance (Y), Difference of the components of color of blue (CB), Difference of the components of color of red (CR), (*Gonzalez et al., 2009*Gonzalez RC, Woods RE & Eddins SL (2009) Digital Image Processing Using MATLAB. 2nd ed. Upper Saddle River, Prentice Hall. 609p.).
YIQ	Luminance (Y), (I and Q) Chrominance that includes the components of color from orange to cyan and from green to magenta respectively, (*Gonzalez et al., 2009*Gonzalez RC, Woods RE & Eddins SL (2009) Digital Image Processing Using MATLAB. 2nd ed. Upper Saddle River, Prentice Hall. 609p.).
TSL	Hue (T), Saturation (S) and Luminance (L), (Gonzalez et al., 2009).
SIFT	Transformation of scale invariant characteristic.
CNN	Deep convolutional neuronal network.
SVM	Vector Support Machine.
ANNs	Artificial neural networks.
A ⊝B	Erode.
A ⊕B	Dilate.
B	Structuring element.
rgb2hsv	Convert from RGB color space to HSV.
rgb2tsl	Convert from RGB color space to TSL.
rgb2yiq	Convert from RGB color space to YIQ.
σ	Deviation.

Methodology	Proposed method	K-means +HSV	K-means +LAB
Results

Brasil

Brasil

Detection of foliar diseases using image processing techniques1 This work is part of the project investigation funded by Colciencias with code 511-3-024-15. 2.

ABSTRACT

Detection of foliar diseases using image processing techniques¹ This work is part of the project investigation funded by Colciencias with code 511-3-024-15. 2.