Plant Disease Identification uses Deep Learning Methods
K. Rahul1, K. Sandeep Varma2, M. Venkata Sreeram3, G. Goutham Subhash Nirmal Kumar4, J. Raghu5
1K. Rahul, Department of IT, SRKREC, Bhimavaram (Andhra Pradesh), India.
2K. Sandeep Varma, Department of IT, SRKREC, Bhimavaram (Andhra Pradesh), India.
3M. Venkata Sreeram, Department of IT, SRKREC, Bhimavaram (Andhra Pradesh), India.
4G. Goutham Subhash Nirmal Kumar, Department of IT, SRKREC, Bhimavaram (Andhra Pradesh), India.
5J. Raghu, Department of IT, SRKREC, Bhimavaram (Andhra Pradesh), India.
Manuscript received on 16 May 2019 | Revised Manuscript received on 10 June 2019 | Manuscript Published on 15 June 2019 | PP: 346-351 | Volume-8 Issue-1S3 June 2019 | Retrieval Number: A10620681S319/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The Farmers in the agriculture sector facing a difficult task in identification of plant diseases. Depending on the human naked eye it is difficult to classify plant diseases because it changes the control policy of one disease to another. Finding of disease effect leaf and healthy leaf is a tricky task. It requires knowledge in the plant diseases and technology for processing the input images. In this scenario Image processing uses a Deep Learning method like Convoulation Neural Network (CNN) for predicting the disease affected leaf or not. In this paper CNN is compared with some machine learning, classification methods like K-nearest neighbor (KNN) , Decision tree, Random Forest, Linear Discriminant Analysis (LDA),support vector machine (SVM) and Logistic Regession.
Keywords: Image Processing, Machine Learning and Deep Laerning.
Scope of the Article: Deep Learning