Anthracnose Detection on Walnut Tree Leaves using Outdoor Image Processing Methods

ماشین های کشاورزی

Article 14, Volume 11, Issue 2 - Serial Number 22, 2021, Pages 317-329   

Document Type: Research Article

DOI: 10.22067/jam.v11i2.82558

Authors

A. Yousefvand; J. Amiri Parian^*

Biosystems Engineering Department, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran

Abstract

Introduction
Control of walnut diseases and pests requires the mapping of the extent of contamination within possible shortest time. Therefore, it is necessary to develop systems to detect and determine the prevalence and location of contamination for researchers and gardeners. Image processing has been proposed as an approach to determine the extent and type of damage to different products in farms and gardens. The aim of this study was to design an algorithm based on the processing of walnut leaf images under natural light conditions in order to provide a rapid and non-destructive detection of diseases for the protection of trees using imaging methods. In this research, the possibility of detecting Anthracnose disease was investigated by processing walnut leaf images. The disease was detected using in situ images taken from the leaves to provide the basis for designing application software on smart mechatronic systems.
 Materials and Methods
Images of leaves on walnut trees were taken under outdoor light conditions. Color and morphological properties extracted from the images were used to detect the pest on the leaves. Gnomonia leptostyla disease diagnostic algorithm was based on process of color and morphological characteristics, leaves background and disease-stained spots. The range of changes in R, G, and B indices was obtained in histograms and then two-dimensional spaces were analyzed statistically on GR, GB, and BR planes. All points from these regions were used as statistical samples, for which bivariate regressions of GR, GB, and BR were obtained as y = b0 + b1x. Segments containing anthracnose spots from the leaves were segregated by extracting the coordinates of the points in each side on the RGB color space cube. Finally, anthracnose content was detected based on the number of spots detected by the algorithms. The percentage of contamination was used to determine the amount of contamination in each imaged area.
Results and Discussion
Examination of the colored spaces indicated that the domain of the anthracnose color components on the GR side has nothing in common with the color components of the leaves. The analysis of color space data revealed that the leaves and anthracnose were more distinguishable on the GB and RB sides, respectively.
 According to the histogram of the HSV color space, anthracnose spots were isolated from the leaves by determining the H range. In the evaluation of the proposed method for diagnosis of anthracnose, the infection severity calculated by the algorithm with the true infection intensity. T-test results for comparing the mean of the two infection intensity samples showed no significant differences between the two groups at 1% probability level.
 Conclusion
The evaluation of the proposed method showed a 98% segregation accuracy for G. leptostyla detection method. Based on the results, the proposed method for detecting anthracnose spots is suitable for determining the contamination severity in the imaged areas.

Keywords

Color features; Image processing; Morphology features; Walnut tree

References

1. Ahmadi, H. R., and J. Amiri Parian. 2015. Detecting oranges on tree by applying a digital image processing based on the shadow density pattern brigh. Journal of Agricultural Machinery 5 (1): 92-100. (In Farsi).

2. Ahmadi, K., H. Gholizadeh, H. R. Ebadzadeh, F. Hatami, R. Hosainpur, H. Abdshah, M. M. Rezaei, and M. Fazl-Estebregh. 2017. Agricultural Statistics. Gardening Products 2017 (Vol. 3). Pages 138 in Technology SaI, ed. Ministry of Agriculture, Program and Budget Deputy Directorate, Department of Statistics and Information. (In Farsi).

3. Anantrasirichai, N., S. Hannuna, and N. Canagarajah. 2017. Automatic Leaf Extraction from Outdoor Images. arXiv preprint arXiv:1709.06437.

4. Barbedo, J. G. A. 2013. Digital image processing techniques for detecting quantifying and classifying plant diseases. Springer Plus 2 (1).

5. Barbedo, J. G. A. 2016. A review on the main challenges in automatic plant disease identification based on visible range images. Biosystems Engineering 144: 52-60.

6. Bundi, S. R., A. Varadharajan, and A. Chinnasamy. 2013. Performance evaluation of various statistical classifiers in detecting the diseased citrus leaves. International Journal of Engineering Science and Technology 5 (2): 298-307.

7. Çakır, Y., M. Kırcı, E. O. Güneş, and B. B. Üstündağ. 2013. Detection of oranges in outdoor conditions. Pages 500-503. 2013 Second International Conference on Agro-Geoinformatics (Agro-Geoinformatics): IEEE.

8. Golzarian, M. R., F. Sadeghi, N. Ghanei, and F. Kazemi. 2014. A qualitative and quantitative approach to assessing the performance of contrast enhancing color indices used in automatic computer vision plant identification system. in 8th National Congress on Agriculture Machinery Engineering & Mechanization. Jan. 2014. Mashhad, Iran. (In Farsi).

9. Hassan, M., and K. Ahmad. 2017. Anthracnose Disease of Walnut-A Review. International Journal of Environment, Agriculture and Biotechnology 2.

10. Keshavarzi, M. 2011. Walnut diseases in Iran: Diagnosis and management. Agricultural education. Karaj, Iran. (In Farsi).

11. Kim, D. G., T. F. Burks, J. Qin, and D. M. Bulanon. 2009. Classification of grapefruit peel diseases using color texture feature analysis. International Journal of Agricultural and Biological Engineering 2 (3): 41-50.

12. Kurtulmus, F., W. S. Lee, and A. Vardar. 2014. Immature peach detection in colour images acquired in natural illumination conditions using statistical classifiers and neural network. Precision Agriculture 15: 57-79.

13. Lavaf Ghazavi, M., and F. Yaghmaei. 2015. Identification and detection of plant pests of pistachio tree leave using texture and color of the image. in Second National Conference on Applied Research in Computer Science and Information Technology. Tehran, Iran. (In Farsi).

14. Mahdiani, M., R. Tabatabaei-Kolor and, M. R. Golzarian. 2015. Detection of Lettuce and Cabbage from Images Taken under Different Lighting Conditions Using an Elliptic Thresholding. Journal of Agricultural Engineering Research 15: 13-26. (In Farsi).

15. Mahmoodi-Eshkaftaki, M., J. Khazaei, K. Vahdati, and M. Taleb. 2011. Walnut disease detection using machine vision. in 1th National Conference on Modern Agriculture Sciences and Technologies. 10-12 Sep. 2011. Zanjan, Iran. (In Farsi).

16. Matsunaga, T. M., D. Ogawa, F. Taguchi-Shiobara, M. Ishimoto, S. Matsunaga, and Y. Habu. 2017. Direct quantitative evaluation of disease symptoms on living plant leaves growing under natural light. Breeding Science: 16169.

17. Nadafzadeh, M., and S. Abdanan Mehdizadeh. 2017. Determination of the most suitable color space for intelligent water stress discrimination for plants inside the greenhouse (Case Study: Coleus). Iranian Journal of Biosystems Engineering 48: 407-418. (In Farsi).

18. Omrani, E., S. S. Mohtasabi, S. Rafiei, S. Hosainpur, and N. A. Nategh. 2014. Apple leaf diseases detection using image analysis techniques. in 8th National Congress on Agriculture Machinery Engineering & Mechanization. Jan. 2014. Mashhad, Iran. (In Farsi).

19. Öztürk, B., M. Kirci, and E. O. Güneş. 2016. Detection of green and orange color fruits in outdoor conditions for robotic applications. Pages 1-5. 2016 Fifth International Conference on Agro-Geoinformatics (Agro-Geoinformatics): IEEE.

20. Pujari, J. D., R. Yakkundimath, and A. S. Byadgi. 2015. Image processing based detection of fungal diseases in plants. Procedia Computer Science 46: 1802-1808.

21. Pydipati, R., T. Burks, and W. Lee. 2006. Identification of citrus disease using color texture features and discriminant analysis. Computers and Electronics in Agriculture 52: 49-59.

22. Rouzegar, M. R., and M. R. Golzarian. 2015. The application of image processing to detect and classify diseases of plants and fruits. in 2th National Conference of Modern Topic in Agriculture. Oct. 2015. Tehran, Iran. (In Farsi).

23. Saremi, H., S. R. Rezazahshemi, and H. Jafari. 2002. Investigating the disease of walnut black (anthracnose) in northwestern Iran. Agricultural Sciences and Natural Resources 9 (4): 141-154. (In Farsi).

24. Singh, V., and A. K. Misra. 2017. Detection of plant leaf diseases using image segmentation and soft computing techniques. Information processing in Agriculture 4: 41-49.

25. Teixido, M., D. Font, T. Pallejà, M. Tresanchez, M. Nogues, and J. Palacin. 2012. Definition of linear color models in the RGB vector color space to detect red peaches in orchard images taken under natural illumination. Sensors 12: 7701-7718.

26. Tripathi, G., and J. Save. 2015. An image processing and neural network based approach for detection and classification of plant leaf diseases. Journal Impact Factor 6: 14-20.