International Journal of Advanced Innovative Technology in Engineering (IJAITE)

---

Plant Disease Detection Using Convolutional Neural Network

Mrunali M. Wankhade, Jui M. Manorkar, Amitkumar Manekar

Abstract :

The latest generation of convolutional neural networks (CNNs) has achieved important results in the field of image classification. This project is based with a new approach to the development of plant disease and recognition model for the detection process, based on leaf image classification, by the use of deep convolutional networks. Important way of training and the methodology is used to facilitate a quick and very easy system implementation in practice. This project is able to observed 13 different types of plant diseases out of all healthy leaves, with the ability to distinguish plant leaves from their surroundings. According to our paper, this method for plant disease recognition has been proposed for the first time. All important process required for implementing this disease recognition model are fully described throughout the paper, starting from collecting images in order to create a database or information, proceed by agricultural experts. A deep learning framework developed by Berkley Vision and Learning Centre, was used to perform the deep CNN training for the plant detection. The result of the experiment on the developed model achieved precision between 91% and 98%, for separate class tests, on average 96.3%.

Keywords :

Full Text :

Download PDF

DOI :

Cite this paper :

References :

---