IJBTT

Leaf Disease Prediction Using Fast Enhanced Learning Method

Leaf Disease Prediction Using Fast Enhanced Learning Method
	© 2021 by IJETT Journal
	Volume-69 Issue-9
	Year of Publication : 2021
	Authors : M.Thanjaivadivel, R.Suguna
	DOI :  10.14445/22315381/IJETT-V69I9P205

How to Cite?

M.Thanjaivadivel, R.Suguna, "Leaf Disease Prediction Using Fast Enhanced Learning Method," International Journal of Engineering Trends and Technology, vol. 69, no. 9, pp. 34-44, 2021. Crossref, https://doi.org/10.14445/22315381/IJETT-V69I9P205

Abstract
More than 75% of world poverty can be reduced by the process of Agriculture. Based on the previous studies, due to the increase in plant disease, 40% of production in agriculture is in the loss. To prevent and control plant diseases, the key link is to detect the disease in the leaf parts. This paper takes tomato leaves with 10 classes, and apple leaves with 4 classes, grapes leave with 4 classes, Corn or maize leaf with 4 classes, and potato leaves with 3 classes as experimental data [18]. The Plant Village dataset available online has been collected for the purpose of training and testing the algorithms. For the process of training, the dataset has been classified into two major classes as healthy and unhealthy. And it was further classified into subclasses based on the category of disease. For the texture-based feature GLCM, haralick texture has been used, and the color histogram is used for color feature extraction, and for shape-based feature Hu moments, Zernike moments have been used. Then the proposed algorithm has been trained to predict the disease and the exact type of the disease the plant got affected with more accuracy. The corn disease has been tested with various existing algorithms like logistic regression, linear discriminant analysis, KNN, Classification and regression tree, Random Forest, Naïve Bayes with an accuracy of 78.0625,77.1875, 75. 5625, 77.75 ,85.3125, 55.375 and 78.125 respectively. Further, the images have been tested using the proposed algorithm as well, which gives an accuracy of 99.76%. Similarly tested for apple, grapes, potato, and corn or maize. When compared with the mentioned existing algorithms, the proposed extreme learning algorithm predicts the disease with more accuracy.

Keywords
Image Classification, Leaf Disease, CNN, KMeans clustering, NN Classifier, SVM

Reference
[1] Jogekar, R. N., & Tiwari, N. (2021). A review of deep learning techniques for identification and diagnosis of plant leaf disease. Smart Trends in Computing and Communications: Proceedings of SmartCom 2020, 435-441.
[2] K C Gouda, Libujashree R, Priyanka Kumari, Manisha Sharma, Ambili D Nair "An Approach for Rainfall Prediction using Soft Computing" International Journal of Engineering Trends and Technology 67.3 (2019): 158-164.
[3] Pham, T. N., Van Tran, L., & Dao, S. V. T. (2020). Early Disease Classification of Mango Leaves Using Feed-Forward Neural Network and Hybrid Metaheuristic Feature Selection. IEEE Access, 8, 189960-189973.
[4] Argüeso, D., Picon, A., Irusta, U., Medela, A., San-Emeterio, M. G., Bereciartua, A., & Alvarez-Gila, A. (2020). Few-Shot Learning approach for plant disease classification using images taken in the field. Computers and Electronics in Agriculture, 175, 105542.
[5] Rao, A., & Kulkarni, S. B. (2020). A hybrid approach for plant leaf disease detection and classification using digital image processing methods. The International Journal of Electrical Engineering & Education, 0020720920953126.
[6] Arcidiacono, C. (2020). Webinars Cycle Sustainable and Environmentally Safe Plant Health Care in a Technologically Advanced Agriculture> to celebrate IYPH 2020 proclaimed by FAO WEBINAR Data Sharing and other Open (Doctoral dissertation, Sainsbury Laboratory).
[7] Xie, X., Ma, Y., Liu, B., He, J., Li, S., & Wang, H. (2020). A deep-learning-based real-time detector for grape leaf diseases using improved convolutional neural networks. Frontiers in plant science, 11.
[8] Kuznetsova, A., Maleva, T., & Soloviev, V. (2020). Using YOLOv3 algorithm with pre-and post-processing for apple detection in the fruit-harvesting robot. Agronomy, 10(7), 1016.
[9] Nazki, H., Yoon, S., Fuentes, A., & Park, D. S. (2020). Unsupervised image translation using adversarial networks for improved plant disease recognition. Computers and Electronics in Agriculture, 168, 105117.
[10] Lohithashva, B. H., Aradhya, V. M., & Guru, D. S. (2020). Violent video event detection based on integrated LBP and GLCM texture features. Revue d’Intelligence Artificielle, 34(2), 179-187.
[11] Farhan, A. H., & Kamil, M. Y. (2020, November). Texture Analysis of Breast Cancer via LBP, HOG, and GLCM techniques. In IOP Conference Series: Materials Science and Engineering (Vol. 928, No. 7, p. 072098). IOP Publishing.
[12] Anggraini, R. A., Wati, F. F., Shidiq, M. J. F., Suryadi, A., Fatah, H., & Kholifah, D. N. (2020). Identification Of Herbal Plant Based On Leaf Image Using Glcm Feature And K-Means. Jurnal Techno Nusa Mandiri, 17(1), 71-78.
[13] Kumara, S. (2020, February 9). Identification Of Nitrogen Status In Brassica Juncea L.Using Color Moment Glcm And Backpropagation Neural Network. https://doi.org/10.31219/osf.io/cmg2b
[14] https://www.kaggle.com/abdallahalidev/plantvillage-dataset
[15] https://www.kaggle.com/thanjaivadivelm/tomato
[16] Kumar, A., Razi, R., Singh, A., & Das, H. (2020, July). Res-VGG: A Novel Model for Plant Disease Detection by Fusing VGG16 and ResNet Models. In International Conference on Machine Learning, Image Processing, Network Security and Data Sciences (pp. 383- 400). Springer, Singapore.
[17] https://extension.umn.edu/diseases/late-blight
[18] https://extension.umn.edu/diseases/early-blight-tomato