Automated Plant Disease Detection using Deep Learning Architectures with Autonomous rover
Jothilakshmi R1, Sharanesh R2

1Dr. Jothilakshmi R*, Department of Information Technology, R.M.D Engineering College, Chennai, India.
2Sharanesh R, Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India. 

Manuscript received on May 25, 2020. | Revised Manuscript received on June 29, 2020. | Manuscript published on July 30, 2020. | PP: 248-254 | Volume-9 Issue-2, July 2020. | Retrieval Number: B3469079220/2020©BEIESP | DOI: 10.35940/ijrte.B3469.079220
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Agriculture is the backbone and plays a vital role in many Asian countries. Farmers mainly depend on their agricultural produce for their living. A report says one-third of the farmers income account’s for the agricultural loss which is primarily due to plant diseases. To combat this farmers are in need of a early plant disease identification mechanism. Observation of individual plants in the farm for detecting the disease is labor-intensive and time consuming work, if the farm is vast and multiple plants are cultivated then it’s even worse. To solve such issues, current technologies like the Internet of Things (IoT) and artificial intelligence (AI) and Machine Learning (ML) are used to predict the diseases more effectively. Farmers usually detect plant diseases with the help of images captured manually and analyzed separately by experts. The proposed system renders an efficient solution for detecting multiple diseases in several plant varieties. The system is designed to detect and recognize several plant varieties, specifically pepper, grapes, and strawberry. The proposed system discovers various plant’s various diseases based on the inputs obtained by capturing images from a built-in camera present in the Autonomous rover. The rover also record’s it’s GPS location and makes a map of the entire farm traced and checked by the robot. The images are processed and are classified into their respective categories using deep learning algorithms. Convolutional neural networks the powerful methodology for image classification is the underlying principle applied. The deep learning model’s architecture namely, VGG16 and InceptionResNetV2, are used to train the model. These models are primarily made of convolutional layers. On testing, we recorded am accuracy of 93.21% was obtained from VGG16, and 95.24% from InceptionResNetV2. 
Keywords: Deep learning, Disease detection, Precision farming, Convolutional Neural Networks(CNN), Location mapping, VGG16, InceptionResNetV2