Agricultural Informatics

6Deep Neural Network-Based Multi-Class Image Classification for Plant Diseases

Alok Negi¹, Krishan Kumar^1* and Prachi Chauhan²

¹Department of Computer Science and Engineering, National Institute of Technology, Srinagar, India²College of Technology, G.B. Pant University of Agriculture and Technology, Pantnagar, India

Abstract

Recognition of plant disease is significantly a difficult challenge in agriculture farming field. Faster and more accurate prediction of leaf diseases in plants will help to improve crop production and market value in an effective management strategy while dramatically reducing environmental damage. Disease detection in plant needs a lot hard work, knowledge of all plant diseases with more processing time. Hence, plant disease recognition is the majority promising approach in agriculture, which is attracting significant attention in both the farming and computer communities. Therefore, in this paper we describe Deep Convolutional Neural Network (CNN) model to care for farming by identifying leaf disease that help in growing up the healthy plants. We apply CNN techniques on large agricultural plant dataset for accurate detection of plant leaves diseases.

Keywords: CNN, dropout, normalization, plant disease

6.1 Introduction

Agriculture sector plays a crucial role in establishing young crop seedlings to be raised or handled until they become ready for much more mandatory and durable seeding. According to the IPCC [1], possible impact of climate change includes ...