Evrişimli Sinir Ağı ile Çeltik Bitkisi Hastalığının Tespiti

Dünya çapında pirinç tüketimi göz önüne alındığında pirincin önemli bir yere sahip olduğu görülür. Çeltik bitkisi, buğdaygiller ailesinden mısır ve buğdaydan sonra en fazla ekimi yapılan bitkidir. Tarım alanındaki son araştırma konularından biriside, bir bitkinin yaprak görüntülerinden hastalıkların tanınması veya sınıflandırılmasıdır. Yaprak görüntülerinden çeltik hastalığının otomatik bir şekilde teşhis edilmesi, geliştirme aşamasında olan bir araştırma konusudur. Bu gelişime katkı sağlamak amacıyla farklı öğrenme yöntemleri kullanılarak hastalığın erken teşhisi için önemli çalışmalar yapılmaktadır. Bu çalışmada temel olarak hastalıkları tespit etmek için bir makine öğrenme yöntemi olan derin öğrenme modelleri kullanılmıştır. Bu çalışmada derin Evrişimli Sinir Ağı (ESA) kullanılarak çeltik bitkisinin hastalıklı olup olmadığı tespit edilmiştir. Çalışmada kullanılan 5000 adet çeltik bitkisi yaprağına ait veri seti Kaggle sitesinden alınmıştır. Hastalığın tespiti için çeltik bitkisine ait üç hastalık (BrowSpot, LeafBlast ve Hispa) ve sağlıklı olmak üzere toplam iki sınıflı sınıflandırma yapılmıştır. Çeltik bitkisinin hastalığının tespiti için kullanılan ESA'nın hiper-parametrelerinde değişiklik yapılarak %91,54’lük bir başarım oranı elde edilmiştir. Veri artırma yöntemiyle veri setindeki 5000 görüntüden 8000 çeltik bitki yaprağı görüntüsü elde edilmiş ve ESA için bu görüntüler üzerinden yapılan eğitimden sonra %94,87’lik bir başarım oranı elde edilmiştir. Kullanılan veri setindeki görüntüler üzerinden ön işlem yapıldıktan sonra ESA ile eğitim işleminden sonra %97,57’lik bir başarım oranı elde edilmiştir.

Detection of Disease of Rice Plant with Convolutional Neural Network

Considering the worldwide rice consumption, it is seen that rice has an important place. The rice plant is the most cultivated plant after corn and wheat from the grass family. One of the latest research topics in agriculture is the recognition or classification of diseases from images of a plant's leaves. Automatic diagnosis of rice disease from leaf images is a research subject under development. In order to contribute to this development, important studies are carried out for the early diagnosis of the disease by using different learning methods. In this study, deep learning models, which is a machine learning method, were used to detect diseases. In this study, it was determined whether the rice plant was diseased or not by using the deep Convolutional Neural Network (CNN). The data set of 5000 rice plant leaves used in the study was taken from the Kaggle website. In order to detect the disease, a total of two classifications were made as three diseases of the rice plant (BrowSpot, LeafBlast and Hispa) and healthy. An accuracy rate of 91.54% was obtained by modifying the hyper-parameters of ESA, which is used to detect the disease of rice plant. With the data augmentation method, 8000 rice plant leaf images were obtained from 5000 images in the data set and an accuracy rate of 94.87% was obtained after training on these images for ESA. After preprocessing on the images in the used dataset, an accuracy rate of 97.57% was obtained after training with ESA.

PDF

___

[1] S. Weizheng, W. Yachun, C. Zhanliang, and W. Hongda, “Grading method of leaf spot disease based on image processing,” in 2008 International Conference on Computer Science and Software Engineering, 2008.
[2] “Rice Production (Peace Corps): Chapter 14 – Diseases of rice,”. [Online]. Available: http://www.nzdl. [Accessed: 19-Oct-2021].
[3] B. ChandraKarmokar, M. Samawat Ullah, M. Kibria Siddiquee, and K. Md. Rokibul Alam, “Tea leaf diseases recognition using neural network ensemble,” Int. J. Comput. Appl., vol. 114, no. 17, pp. 27–30, 2015.
[4] G. Wang, Y. Sun, and J. Wang, “Automatic image-based plant disease severity estimation using deep learning,” Comput. Intell. Neurosci., vol. 2017, pp. 1–8, 2017.
[5] A. Fuentes, S. Yoon, S. Kim, and D. Park, “A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition,” Sensors (Basel), vol. 17, no. 9, p. 2022, 2017.
[6] S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic, “Deep neural networks based recognition of plant diseases by leaf image classification,” Comput. Intell. Neurosci., vol. 2016, p. 3289801, 2016.
[7] J. Lu, J. Hu, G. Zhao, F. Mei, and C. Zhang, “An in-field automatic wheat disease diagnosis system,” Comput. Electron. Agric., vol. 142, pp. 369–379, 2017.
[8] R. Bhagawati, K. Bhagawati, A. Singh, R. Nongthombam, R. Sarmah, G. Bhagawati, “Artificial Neural Network Assisted Weather Based Plant Disease Forecasting System”, IJRITCC, vol. 3, no. 6, pp. 4168– 4173, Jun. 2015.
[9] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using deep learning for image-based plant disease detection,” Front. Plant Sci., vol. 7, pp: 1419, 2016.
[10] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, vol. 60, no. 6, pp. 84–90, 2017.
[11] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv [cs.CV], 2014.
[12] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[13] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[14] M. Kerkech, A. Hafiane, and R. Canals, “Deep leaning approach with colorimetric spaces and vegetation indices for vine diseases detection in UAV images,” Comput. Electron. Agric., vol. 155, pp. 237–243, 2018.
[15] J. Ma, K. Du, F. Zheng, L. Zhang, Z. Gong, and Z. Sun, “A recognition method for cucumber diseases using leaf symptom images based on deep convolutional neural network,” Comput. Electron. Agric., vol. 154, pp. 18–24, 2018.
[16] Y. Lu, S. Yi, N. Zeng, Y. Liu, and Y. Zhang, “Identification of rice diseases using deep convolutional neural networks,” Neurocomputing, vol. 267, pp. 378–384, 2017.
[17] H. B. Prajapati, J. P. Shah, and V. K. Dabhi, “Detection and classification of rice plant diseases,” Intell. Decis. Technol., vol. 11, no. 3, pp. 357–373, 2017.
[18] C. R. Rahman et al., “Identification and recognition of rice diseases and pests using convolutional neural networks,” Biosyst. Eng., vol. 194, pp. 112–120, 2020.
[19] C. DeChant et al., “Automated identification of northern leaf blight-infected maize plants from field imagery using deep learning,” Phytopathology, vol. 107, no. 11, pp. 1426–1432, 2017.
[20] B. Liu, Y. Zhang, D. He, and Y. Li, “Identification of apple leaf diseases based on deep convolutional neural networks,” Symmetry (Basel), vol. 10, no. 1, pp: 11, 2017.
[21] R. R. and D. Park, “A multiclass deep convolutional neural network classifier for detection of common rice plant anomalies,” Int. J. Adv. Comput. Sci. Appl., vol. 9, no. 1, 2018.
[22] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
[23] H. Durmus, E. O. Gunes, and M. Kirci, “Disease detection on the leaves of the tomato plants by using deep learning,” in 2017 6th International Conference on Agro-Geoinformatics, 2017.
[24] “Tf.Keras.Preprocessing.Image.ImageDataGenerator,” TensorFlow. [Online]. Available: https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/image/ImageDataGenerator. [Accessed: 08-Jan-2022].