Automatic Olive Peacock Spot Disease Recognition System Development by Using Single Shot Detector

Among the artificial intelligence based studies conducted in the field of agriculture, disease recognition methods founded on deep learning are observed to become widespread. Due to the diversity and regional specificity of many plant species, studies performed in this field are not at the desired level. Olive peacock spot disease of the olive plant which grows only in certain regions in the world is a widely encountered disease particularly in Turkey. The aim of this research is to develop an olive peacock spot disease detection system using a Single Shot Detector (SSD) which is one the popular deep learning architectures to support olive farmers. This study presents a data set consisting of 1460 olive leaves samples for the detection of olive peacock spot disease. All of the images of the olive leaves which produced under controlled conditions were collected from Aegean region of Turkey during spring and summer. The data set was trained with different intersection over union (IoU) threshold values using SSD architecture. A 96% average precision (AP) value was obtained with IoU=0.5. As IOU value goes up from 0.5, erroneously classified olive peacock spot disease symptoms growed larger as well. The AP curve becomes flat when between 0.1 and 0.5, and it decreases when greater than 0.5. This analysis showed that the IoU significantly influenced the performance of SSD based model in detection of olive peacock spot disease. In addition to, trainings were performed by employing Pytorch library and a GUI was developed for the SSD based application using PyQt5 which is one of Pyhton's libraries. Results showed that the SSD was a robust tool for recognizing the olive peacock spot disease.

Single Shot Detector Kullanarak Otomatik Zeytin Halkalı Leke Hastalığı Tanıma Sistemi Geliştirilmesi

Tarım alanında gerçekleştirilen yapay zekâ temelli çalışmalar arasında, derin öğrenmeye dayanan hastalık tespiti uygulamalarının giderek yaygınlaştığı görülmektedir. Bitki türleri arasındaki çeşitlilik ve çoğu bitki türünün belirli coğrafyalarda yetişmesi bu alanda gerçekleştirilen çalışmaların sayısının istenen düzeyde olmadığını göstermektedir. Dünyada sadece belirli bölgelerde yetişen zeytin bitkisine ait halkalı leke hastalığı özellikle Türkiye’de yaygın olarak görülmektedir. Bu çalışmanın amacı, zeytin çiftçilerini desteklemek için popüler derin öğrenme mimarilerinden birisi olan Single Shot Detector (SSD) kullanarak zeytin halkalı leke hastalığını tespit sistemi geliştirmektir. Bu çalışmada zeytin halkalı leke hastalığının tespiti için 1460 adet zeytin yaprağı örneğini içeren veri seti oluşturulmuştur. Kontrollü koşullar altında üretilen tüm zeytin yaprak görüntüleri ilkbahar ve yaz dönemlerinde Türkiye’nin Ege bölgesinden toplanmıştır. Veri seti, SSD mimarisi üzerinde farklı IoU treshold değerleri ile eğitilmiştir. IoU=0.5 için %96 düzeyinde Average Precision (AP) değeri elde edilmiştir. IOU değeri 0.5’den yukarı doğru gittikçe, düşüş hatalı olarak sınıflandırılan olive peacock spot semptomu sayısının arttığı görülmüştür. AP eğrisi 0.1 ile 0.5 arasındayken düz hale gelir ve 0.5’den büyük olduğunda azalır. Bu analiz IoU’nun zeytin halkalı leke hastalığının tespitinde SSD temelli modelin performansını önemli şekilde etkilediğini göstermektedir. Ayrıca eğitimler Pytorch kütüphanesi kullanılarak gerçekleştirildi ve Python kütüphanelerinden biri olan PyQt5 kullanılarak SSD tabanlı uygulama için bir GUI geliştirildi. Sonuçlar, SSD’nin olive peacock spot hastalığının tanınması için güçlü bir araç olduğunu göstermiştir.

PDF

___

[1] I. Sa, Z. Ge, F. Dayoub, B. Upcroft, T. Perez, and C. McCool, "Deepfruits: A fruit detection system using deep neural networks," Sensors, vol. 16, p. 1222, 2016.

[2] J. Lu, J. Hu, G. Zhao, F. Mei, and C. Zhang, "An in-field automatic wheat disease diagnosis system," Computers and electronics in agriculture, vol. 142, pp. 369-379, 2017.

[3] O. Apolo-Apolo, J. Martínez-Guanter, G. Egea, P. Raja, and M. Pérez-Ruiz, "Deep learning techniques for estimation of the yield and size of citrus fruits using a UAV," European Journal of Agronomy, vol. 115, p. 126030, 2020.

[4] M. Kerkech, A. Hafiane, and R. Canals, "Deep leaning approach with colorimetric spaces and vegetation indices for vine diseases detection in UAV images," Computers and electronics in agriculture, vol. 155, pp. 237-243, 2018.

[5] M. M. Ozguven and K. Adem, "Automatic detection and classification of leaf spot disease in sugar beet using deep learning algorithms," Physica A: Statistical Mechanics and its Applications, vol. 535, p. 122537, 2019.

[6] M. G. Selvaraj, A. Vergara, H. Ruiz, N. Safari, S. Elayabalan, W. Ocimati, et al., "AIpowered banana diseases and pest detection," Plant Methods, vol. 15, p. 92, 2019.

[7] W. Li, P. Chen, B. Wang, and C. Xie, "Automatic localization and count of agricultural crop pests based on an improved deep learning pipeline," Scientific reports, vol. 9, pp. 1-11, 2019.

[8] A. Fuentes, S. Yoon, S. C. Kim, and D. S. Park, "A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition," Sensors, vol. 17, p. 2022, 2017.

[9] G. Polder, N. van de Westeringh, J. Kool, H. A. Khan, G. Kootstra, and A. Nieuwenhuizen, "Automatic Detection of Tulip Breaking Virus (TBV) Using a Deep Convolutional Neural Network," IFAC-PapersOnLine, vol. 52, pp. 12-17, 2019.

[10] D. Rong, L. Xie, and Y. Ying, "Computer vision detection of foreign objects in walnuts using deep learning," Computers and Electronics in Agriculture, vol. 162, pp. 1001-1010, 2019.

[11] P. V. Bhatt, S. Sarangi, and S. Pappula, "Detection of diseases and pests on images captured in uncontrolled conditions from tea plantations," in Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping IV, 2019, p. 1100808.

[12] B. A. Ashqar and S. S. Abu-Naser, "Image-based tomato leaves diseases detection using deep learning," International Journal of Academic Engineering Research, vol. 2, pp. 10-16, 2018.

[13] C. IO. (2018, 13 December 2019). World oil production. Available: https://www.internationaloliveoil.org/what-we-do/economic-affairs-promotion-unit/

[14] F. O. Obanor, M. V. Jaspers, E. E. Jones, and M. Walter, "Greenhouse and field evaluation of fungicides for control of olive leaf spot in New Zealand," Crop Protection, vol. 27, pp. 1335- 1342, 2008.

[15] A. C. Cruz, A. Luvisi, L. De Bellis, and Y. Ampatzidis, "X-FIDO: An effective application for detecting olive quick decline syndrome with deep learning and data fusion," Frontiers in plant science, vol. 8, p. 1741, 2017.

[16] M. Alruwaili, S. Alanazi, S. A. El-Ghany, and A. Shehab, "An Efficient Deep Learning Model for Olive Diseases Detection," International Journal of Advanced Computer Science and Applications, vol. 10, 2019.

[17] S. Ren, K. He, R. Girshick, and J. Sun, "Faster r-cnn: Towards real-time object detection with region proposal networks," in Advances in neural information processing systems, 2015, pp. 91-99.

[18] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, et al., "Ssd: Single shot multibox detector," in European conference on computer vision, 2016, pp. 21-37.

[19] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.

[20] A. Kaya, A. S. Keceli, C. Catal, H. Y. Yalic, H. Temucin, and B. Tekinerdogan, "Analysis of transfer learning for deep neural network based plant classification models," Computers and electronics in agriculture, vol. 158, pp. 20-29, 2019.

[21] S. Uğuz and N. Uysal, "Classification of olive leaf diseases using deep convolutional neural networks", Neural Computing and Applications, https://doi.org/10.1007/s00521-020-05235-5.

[22] S. Cao, D. Zhao, X. Liu, and Y. Sun, "Real-time robust detector for underwater live crabs based on deep learning," Computers and Electronics in Agriculture, vol. 172, p. 105339, 2020.

[23] A. Ramcharan, P. McCloskey, K. Baranowski, N. Mbilinyi, L. Mrisho, M. Ndalahwa, et al., "A mobile-based deep learning model for cassava disease diagnosis," Frontiers in plant science, vol. 10, p. 272, 2019.

[24] S. Uğuz, Makine Öğrenmesi Teorik Yönleri ve Python Uygulamaları ile Bir Yapay Zeka Ekolü: Nobel Akademik Yayıncılık, 2019.