Diagnosis of Blight Diseases in Tea Leaves Using Hybrid Deep Learning Approach

By : V. Sujatha, Nirmala V, Simi Margarat G, Ravindrakumar Selvaraj

Page No: 119-128

Abstract
Identification of leaf disease in tea plant in early stage is important to increase the production. In research so far in literature several artificial and machine learning approaches are investigated. In this paper, a new deep learning method is proposed combining the properties of GLCM, CNN and RNN. The method was developed for the diagnosis of disease using three types of data of tea leaf samples. The complex features were extracted from leaf samples. The extracted features were feed to the RNN classifier to differentiate abnormal and normal cases. The Investigation for disease classification is undergone using different pretrained CNN models, reshaping and feature map setting is done. The model is trained with the help of the Plant Village Dataset consisting of 54,305 images comprising of 38 different classes of both unhealthy and healthy leaves. The disease classification accuracy achieved by the proposed architecture is up to 95.81% and various observations were made with different hyperparameters of the CNN architecture. The experiment results achieved are comparable with other existing techniques in literature.

Authors :
V. Sujatha : Department of ECE, Shree Sathyam College of Engineering and Technology, Sankari, Tamil Nadu, India
Nirmala. V : Department of ECE, Assistant Professor, M. Kumarasamy College of Engineering, Karur, Tamil Nadu, India
Simi Margarat G : Department of Computer Science and Engineering, New Prince Shri Bhavani College of Engineering and Technology, Chennai, India
Ravindrakumar Selvaraj : Associate Professor, Biomedical Engineering, KIT- KalaignarKarunanidhi Institute of Technology, Coimbatore, Tamil Nadu, India
 

DOI: https://doi.org/10.32381/JPSR.2023.39.03.12