توسعه یک سامانه ترکیبی جدید به منظور تشخیص بیماری های برگ درخت سیب

نوع مقاله : مقاله پژوهشی

نویسندگان

1 ماشین های کشاورزی، دانشکده مهندسی و فناوری دانشگاه تهران

2 دانشگاه تهران

3 مهندسی عمران،دانشکده عمران محیط زیست دانشگاه امیرکبیر

چکیده

هر ساله بیماری­های گیاهی موجب خسارت­های قابل توجهی در بخش کشاورزی می­شوند که می­توان تأثیر آن­را در چرخه­ی اقتصادی کشورها و امنیت غذایی مردم احساس نمود. تشخیص زودهنگام بیماری­های گیاهی راهکاری مفید برای کاهش این خسارت­ها می­باشد. در سال­های اخیر محققان مختلف از روش­هایی چون تصویربرداری برای تشخیص بیماری­های گیاهی استفاده نموده­اند. در این تحقیق یک سامانه جدید، متشکل از روش پردازش تصویر دیجیتال و مدل ترکیبی شبکه عصبی به­منظور تشخیص سه بیماری برگ درخت سیب (بیماری­های لکه سیاه سیب، آلترناریا و آفت مینوز) بکار گرفته شد. در واقع از فرایند روش پردازش تصویر دیجیتال برای تهیه، پردازش و استخراج ویژگی­های هر یک از تصاویر نمونه­ها و از مدل ترکیبی شبکه عصبی مصنوعی برای طبقه­بندی بیماری­ها استفاده گردید. در این مدل برای آموزش شبکه از دو الگوریتم بهینه­سازی ازدحام ذرات (PSO) و الگوریتم لونبرگ مارکوارت (LM) استفاده شد. در ادامه عملکرد سامانه پیشنهادی در تشخیص بیماری­های درخت سیب مورد ارزیابی قرار گرفته و مشاهده گردید که این سامانه در تشخیص بیماری فوق الذکر با دقت 99 درصد و شاخص­های 985/0= R2 و 099/0= RMSE عملکرد مناسبی دارد و همچنین در مقایسه با سایر روش­های انجام شده توسط دیگر محققان، در تشخیص بیماری­های برگ درخت سیب توانایی بالاتری دارد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Developing a new hybrid system for detection of apple tree leaves diseases

نویسندگان [English]

  • Zohreh Ghasemi Varjani 1
  • Seyed Saeid Mohtasebi 2
  • Hadi Ghasemi 3
  • Elham Omrani 1
1 Department of Agricultural Machinery Engineering, Faculty of Agricultural Engineering and Technology, University of Tehran, Karaj, Iran
2 University of Tehran
3 Department of Civil and Environmental Engineering, Amirkabir University of Technology, Tehran, Iran
چکیده [English]

Each year, plant diseases cause considerable damages to the agricultural sector which their effect on the economy and food security is very important. Early detection of plant diseases is a useful strategy to reduce these losses. In recent years, researchers have used a variety of techniques such as machine vision for the diagnosis of plant diseases. In this study, a new system, consisting of digital image processing technique and also combination model of artificial neural network to distinguish three apple tree leaf diseases (namely Alternaria, apple black spot, and apple leaf miner pest) were used. In short, the process of digital image processing technique involves preparation, processing, and extraction of features of each of the sample images and the hybrid artificial neural network model was used to classify diseases. In this model, particle swarm optimization algorithm for network training (PSO) and Levenberg-Marquardt (LM) were used. After that, the operation of the proposed system for diagnosis of diseases of apple trees was evaluated. It is concluded that the system has a good performance for diagnosis accuracy was 99% and R2=0.985, RMSE=0.099. Finally, in comparison with other methods mentioned by other researchers for diagnosis of apple tree leaves diseases, the proposed system has higher ability.

کلیدواژه‌ها [English]

  • plant diseases
  • image processing
  • artificial neural network
  • Particle Swarm Optimization
Asraf, H. M., Nooritawati, M. T., Shah Rizam, M. S. B. (2012). A Comparative Study in Kernel-Based Support Vector Machine of Oil Palm Leaves Nutrient Disease, Journal of Procedia Engineering, 41, 1353–1359.
Billah, M., Miah, M. B. A., Hanifa, A. and Ruhul Amin, M. d. (2015). Adaptive Neuro Fuzzy Inference System based Tea Leaf Disease Recognition using Color Wavelet Features, Journal of Communications on Applied Electronics, 3(5), 1–4.
Eberhart, R. and Kennedy, J. (1995). A new optimizer using particle swarm theory, Journal of IEEE Service Center, 39–43.
Fang, J., Zhang, C., Wang, S. (2008). Application of genetic algorithm (GA) trained artificial neural to identify tomatoes with physiological, Journal of Computer and Computing Technologies in Agriculture, 259, 1103-1111.
Food and Agriculture Organization. (2013). Statistics: Crops (Production) in FAO. Retrieved January 12, 2013, From http://www.fao.org/faostat/en/#data/QC
Kumar, A., Lee, W. S., Ehsani, R. J., Albrigo, G., Yang, C., Mangan, R. L.  (2012). Citrus greening disease detection using aerial hyperspectral and multispectral imaging techniques, Journal of Applied Remote Sensing, 6, 1–22.
Loutfi, A., Coradeschi, S., Mani, G.K., Shankar, P. Rayappan, J.B. (2015). Electronic noses for food quality: a review. Journal of Food Engineering, 144, 103–111.
Mahlein, A. K., Steiner, U., Hillnhütter, C., Dehne, H. W., Oerke, E. C. (2012). Hyperspectral imaging for small-scale analysis of symptoms caused by different sugar beet diseases, Journal of Plant Methods, 1–13.
Massimo, F. R, Daciana, I., Clarkson, J. P., Covington, J. A. (2016). Early identification of potato storage disease using an array of metal-oxide based gas sensors, Journal of Postharvest Biology and Technology, 116, 50–58.
Omrani, E. (2013). Plant Diseases Detection Using Image Processing Technique. M. Sc. Thesis, University of Tehran, College of Agriculture and Natural Resources. (In Farsi)
Omrani, E., Khoshnevisan, B., Shamshirband, S., Saboohi, H., Anuar, N. B., Nasir, M. H. N. M. (2014). Potential of radial basis function-based support vector regression for apple disease detection, Journal of Measurement, 55, 512–519.
Pan, L., Zhang, W., Zhu, N., Mao, Sh., Wangd, J., Tu, K. (2014). Early detection and classification of pathogenic fungal disease in post-harvest strawberry fruit by electronic nose and gas chromatography–mass spectrometry, Journal of Food Research International, 62, 162–168.
Tian, J., Qiuxia, H., Xiaoyi, M. A., Mingyu, H. A. N. (2012). An Improved KPCA/GA-SVM Classification Model for Plant Leaf Disease Recognition, Journal of Computational Information Systems, 33, 7737–7745.
Tian, X., Wang, J. & Cui, S. (2013). Analysis of pork adulteration in minced mutton using electronic nose of metal oxide sensors. Journal of Food Engineering, 119(4), 744–749.
UGA Extension. (2014). Georgia Plant Disease Loss Estimates 2014. AP 102-7, From http://extension.uga.edu/publications/detail.cfm?number=AP102-7
Yeh, Y. H., Chung W. C., Liao, J.Y., Chung, C. L., Kuo, Y. F. and Te, L. T. (2016). Strawberry foliar anthracnose assessment by hyperspectral imaging, Journal of Computers and Electronics in Agriculture, 122, 1–9.
Zhanga, Z., Hea, X., Sunb, X., Guoc, L., Wangd, J., Wangd, F. (2015). Image Recognition of Maize Leaf Disease Based on GA-SVM, Journal of Chemical Engineering Transactions, 46, 199–204.
Zhang, Sh., Wu, X., You, Zh., Zhang, L. (2017). Leaf image based cucumber disease recognition using sparse representation classification, Journal of Computers and Electronics in Agriculture, 134, 135–141.