تشخیص بیماری بلاست گیاه برنج در شرایط محیطی مختلف با استفاده از تکنیک پردازش تصویر

نویسندگان
1 دانشیار، گروه مهندسی بیوسیستم، دانشگاه محقق اردبیلی، اردبیل، ایران.
2 دانشجوی دکتری، گروه مهندسی بیوسیستم، دانشگاه محقق اردبیلی، اردبیل، ایران.
3 پژوهشگر پسادکتری، گروه مهندسی بیوسیستم، دانشگاه تربیت مدرس، تهران، ایران.
چکیده
هدف از این تحقیق ارزیابی تکنیک پردازش تصویر در تشخیص بیماری بلاست گیاه برنج در شرایط مزرعه­ای و کنترل­شده می­باشد. با استفاده از نرم­افزار Matlab، تصاویر تهیه شده از شرایط مزرعه­ای و کنترل شده، در سه فضای رنگی RGB، HSI و LAB پردازش شدند. پس از حذف پس­زمینه در فضاهای رنگی RGB، HSI و LAB به تشخیص لکه­های بیماری روی برگ گیاه برنج پرداخته شد. در فضای رنگی RGB با استفاده از تفریق آرایه­ها بصورت آزمون و خطا لکه­های بلاست روی برگ از بقیه پیکسل­های تصویر تفکیک شد. در فضای رنگی HSI از Hue استفاده شد؛ چون این مؤلفه مستقل از تغییرات شدت نور بود، شناسایی لکه بلاست نسبت به مؤلفه­های S و I با دقت بالاتری انجام شد. در فضای رنگی LAB از الگوریتم خوشه­بندی Kmeans برای بخش­بندی تصاویر در سه خوشه استفاده گردید و پس از برچسب گذاری تصویر لکه­های بیماری بلاست در یک خوشه مستقل نمایش داده شد. در پایان جهت تعیین میزان کارایی الگوریتم­های طراحی شده در سه فضای رنگی، فاکتور حساسیت، ویژگی و دقت کل بر اساس ماتریس اغتشاش برای 500 نمونه تصویر تست شد. در شرایط مزرعه­ای و کنترل شده، بالاترین دقت در تشخیص لکه بلاست در فضای رنگی LAB حاصل شد که به ترتیب 94 و 98 درصد بود. به­طورکلی نتایج به­دست آمده نشان داد که روش پردازش تصویر می­تواند برای تشخیص بیماری بلاست گیاه برنج بکار رود.

کلیدواژه‌ها

موضوعات


عنوان مقاله English

Diagnosis of Rice Blast Disease in Different Environmental Conditions using Image Processing Technique

نویسندگان English

Ezzatollah Askari Asli Ardeh 1
mohammad reza larijani 2
Reyhaneh Loni 3
1 university of mohaghegh ardabili
2 university of mohaghegh ardabili
3 Postdoc Researcher, Department of Biosystems Engineering, Tarbiat Modares University, Tehran, Iran
چکیده English

The purpose of this study was to evaluate the image processing technique in rice blast disease detection in field and controlled conditions. Using MATLAB software, images taken from field and controlled conditions were processed in three RGB, HSI and LAB color spaces. Then it was extracted by the gray area intensity profile, color properties, and threshold value for background image removal. After removing background in RGB, HSI and LAB color spaces, disease spots on rice leaf were determined. In RGB color space, by subtracting arrays by test and error, the blast patches on the leaf were separated from the rest of the image pixels. Hue was used in the HSI color space because this component was independent of light intensity variations, so blast blot identification was performed more accurately than the S and I components. In the LAB color space, the Kmeans clustering algorithm was used to segment the images into three clusters and was displayed in an independent cluster after labeling the image of blast disease spots. Finally, in order to determine the performance of the algorithms designed in three color spaces, the sensitivity factor, specificity and total accuracy were tested on the basis of the perturbation matrix for 500 image samples. In field and controlled conditions, the highest accuracy in detecting blast blots in the LAB color space was 94% and 98%, respectively. Overall, the results showed that the image processing method can be used to detect rice blast disease.

کلیدواژه‌ها English

Rice
Disease detection
Image processing
Color space
[1] Mahdavi H, Allahyari M S, Damalas C A, Dunn E S. 2019. Drivers and barriers for organic rice (Oryza sativa L.) production in northern Iran: experts’ consensus using the Delphi method. Biological Agriculture & Horticulture, 1-11.
[2] Kumar K K, Poovannan K, Nandakumar R, Thamilarasi K, Geetha C, Jayashree N, Balasubramanian P. 2003. A high throughput functional expression assay system for a defence gene conferring transgenic resistance on rice against the sheath blight pathogen, Rhizoctonia solani. Plant Science, 165, 5: 969-976.
[3] Larijani M R, Asli‐Ardeh E A, Kozegar E, Loni R. 2019. Evaluation of image processing technique in identifying rice blast disease in field conditions based on KNN algorithm improvement by K‐means. Food Science & Nutrition, 7, 12: 3922-3930.
[4] Jahanbakhshi A, Momeny M, Mahmoudi M, Zhang Y D. 2020. Classification of sour lemons based on apparent defects using stochastic pooling mechanism in deep convolutional neural networks. Scientia Horticulturae, 263, 109133. https://doi.org/10.1016/j.scienta.2019.109133.
[5] Azarmdel H, Mohtasebi S S, Jafari A, Muñoz A R. 2019. Developing an orientation and cutting point determination algorithm for a trout fish processing system using machine vision. Computers and Electronics in Agriculture, 162, 613-629.
[6] Jahanbakhshi A, Kheiralipour K. 2019. Carrot sorting based on shape using image processing, artificial neural network, and support vector machine. Journal of Agricultural Machinery, 9, 2: 295-307. (In Persian).
[7] Umbaugh S E. 2017. Digital Image Processing and Analysis: Applications with MATLAB and CVIPtools. CRC Press.
[8] Nikita K, Deore P J. 2015. Leaf Analysis for Precision Agriculture. International Journal of Advances in Science Engineering and Technology, 3, 4: 144-147.
[9] Gulve P P, Tambe S S, Pandey M A, Kanse M S. 2015. Leaf Disease Detection of Cotton Plant Using Image Processing Techniques. IOSR Journal of Electronics and Communication Engineering (IOSR-JECE), 50-54.
[10] Al Bashish D, Braik M, Bani-Ahmad S. 2011. Detection and classification of leaf diseases using K-means-based segmentation and. Information Technology Journal, 10, 2: 267-275.
[11] Rewar E, Singh B P, Chhipa M K, Sharma O P, Kumari M. 2017. Detection of infected and healthy part of leaf using image processing techniques. Journal of Advanced Research in Dynamical & Control System, 9, 1: 13-19.
[12] Bernardes A A, Rogeri J G, Oliveira R B, Marranghello N, Pereira A S, Araujo A F, Tavares J M R. 2013. Identification of foliar diseases in cotton crop. In Topics in Medical Image Processing and Computational Vision (pp. 67-85). Springer, Dordrecht.
[13] Kahar M A, Mutalib S O F I A N I T A, Rahman A. 2015. Early detection and classification of paddy diseases with neural networks and fuzzy logic. In Proceedings of the 17th International Conference on Mathematical and Computational Methods in Science and Engineering, MACMESE (pp. 248-257).
[14] Koschan A, Abidi M. 2008. Digital color image processing. John Wiley & Sons.
[15] Solomon C, Breckon T. 2011. Fundamentals of Digital Image Processing: A practical approach with examples in Matlab. John Wiley & Sons.
[16] Mongkolchart N, Ketcham M. 2014. The measurement of brown planthopper by image processing. In International Conference on Advanced Computational Technologies & Creative Media (ICACTCM 2014). August 14 – 15, Pattaya, Thailand.
[17] Patil S B, Bodhe S K. 2011. Leaf disease severity measurement using image processing. International Journal of Engineering and Technology, 3, 5: 297-301.
[18] Pydipati R, Burks T F, Lee W S. 2006. Identification of citrus disease using color texture features and discriminant analysis. Computers and Electronics in Agriculture, 52, 2: 49-59.
[19] Arivazhagan S, Shebiah R N, Ananthi S, Varthini S V. 2013. Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features. Agricultural Engineering International: CIGR Journal, 15, 1: 211-217.