Deep Learning Convolutional Neural Network for Apple Leaves Disease Detection

8 Pages Posted: 12 Jun 2019

See all articles by Saraansh Baranwal

Saraansh Baranwal

Jaypee Institute of Information Technology, Noida

Siddhant Khandelwal

Jaypee Institute of Information Technology, Noida – 201309, India

Anuja Arora

Jaypee Institute of Information Technology, Noida – 201309, India

Date Written: February 21, 2019

Abstract

Apple trees are perhaps one of the most popular plants to grow in large plantations and in-home gardens. At the same time, Apple plants are among the plants that are the most prone to diseases. Disease identification at an early stage and its prevention before spreading into other parts of the plant is a challenge even for the expert’s eye. Therefore, an adequate system is required to detect plant disease in the initial stage. This paper displays the prowess of Convolutional Neural Networks to automatically detect and address the issue. Images of Apple leaves, covering various diseases as well as healthy samples, from the Plant Village dataset are used to validate results. Image filtering, image compression, and image generation techniques are used to gain a large train-set of images and tune the system perfectly. The trained model achieves high accuracy scores in all the classes with a net accuracy of 98.54% on the entire dataset, sampled and generated from 2561-labelled images.

Keywords: Plant Leaf Disease Detection, Convolutional Neural Network

Suggested Citation

Baranwal, Saraansh and Khandelwal, Siddhant and Arora, Anuja, Deep Learning Convolutional Neural Network for Apple Leaves Disease Detection (February 21, 2019). Proceedings of International Conference on Sustainable Computing in Science, Technology and Management (SUSCOM), Amity University Rajasthan, Jaipur - India, February 26-28, 2019. Available at SSRN: https://ssrn.com/abstract=3351641 or http://dx.doi.org/10.2139/ssrn.3351641

Saraansh Baranwal (Contact Author)

Jaypee Institute of Information Technology, Noida ( email )

A-10
Sector-62
Noida, Uttar Pradesh 201307
India

HOME PAGE: http://https://in.linkedin.com/in/saraanshbaranwal

Siddhant Khandelwal

Jaypee Institute of Information Technology, Noida – 201309, India ( email )

India

Anuja Arora

Jaypee Institute of Information Technology, Noida – 201309, India ( email )

India

Register to save articles to
your library

Register

Paper statistics

Downloads
54
Abstract Views
247
rank
373,451
PlumX Metrics