Soft-Computing-Based Approaches for Plant Leaf Disease Detection: Machine-Learning-Based Study

Soft-Computing-Based Approaches for Plant Leaf Disease Detection: Machine-Learning-Based Study

Vivek K. Verma (Manipal University Jaipur, India) and Tarun Jain (Manipal University Jaipur, India)
DOI: 10.4018/978-1-5225-8027-0.ch004

Abstract

The disease occurrence phenomena in plants are season-based which is dependent on the presence of the pathogen, crops, environmental conditions, and varieties grown. Some plant varieties are particularly subject to outbreaks of diseases; on the other hand, some are opposite to them. Huge numbers of diseases are seen on the plant leaves and stems. Diseases management is a challenging task. Generally, diseases are seen on the leaves or stems of the plant. Image processing is the best way for the detection of plant leaf diseases. Different kinds of diseases occur because of the attack of bacteria, fungi, and viruses. The monitoring of leaf area is an important tool in studying physiological capabilities associated with plant boom. Plant disorder is usually an unusual growth or dysfunction of a plant. Sometimes diseases damage the leaves of plants.
Chapter Preview
Top

Introduction

Plant diseases cause major production and economic losses in agriculture and forestry. Agriculture in India is one of the biggest sectors of economic development. With increasing population, even though the contribution is continuously falling since independence from 55.1% in 1950 to 14% in 2012, it remained the major employment sector with a marginal difference. Leaf disease detection requires a huge amount of work, knowledge in the plant diseases, and also requires the more processing time. It is crucial to prevent unnecessary waste of financial and other resources, thus achieving healthier production in this changing environment, appropriate and timely disease identification including early prevention has never been more important. India being a tropical region and having three primary seasons- rain, winter, and summer. Most of the crop diseases occur either the Rainy or the Winter Season. Crops in India mostly suffer in the rainy season due to the improper irrigation system. Thus a system needs to be made which can help those farmers in need. We can use Image Processing techniques and Convolution Neural network together for identification of diseases. The basic goal of our project is to help the farmers who want to know what disease their crop has and what is the suitable prevention.

An estimated 15-25 percent of potential crop production is lost due to this menace at a time when India needs not only to raise production but also to ensure the food security and the nutrition for its growing consumption requirements. In 2016 sixth National Agrochemicals Conference was held on the theme of ‘Role of Crop Protection Solutions’. Many topics were brought up by various speakers such as Plasticulture, fertigation, seed treatment, crop protection chemicals, biotechnology, precision farming etc. The conference covered topics of relevance to the sector, incl. Facilitating ease of doing business. Making India global manufacturing hub of quality crop protection solutions, Key issues and challenges faced by the industry, the export potential of the sector as also some of the futuristic technologies such as Vertical Farming.

The very important factor is the detection of plant disease and its issue to prevent a serious blow-up. Automatic detection of plant disease is become to a very important topic of the research. Fungi are diagnosed or determine from their morphology. With few exceptions, bacteria exist as a productive cell and increase in numbers via dividing into cells for the duration of a system called binary fission. In popular, a plant turns into diseased whilst it is continuously disturbed by means of a few causal agents that effects in a peculiar physiological method that disrupts the plant’s regular shape, boom, feature or different activities. This interference with one or greater of a plant’s essential physiological or biochemical systems elicits function pathological conditions or symptoms.

Since the problem has been identified, we need to find a common solution for many types of diseases. There will be some cases where the disease symptoms wouldn’t be visible, or the diseased area coverage is large which would make it hard for the farmers to be able to find a cure, hence a sophisticated analysis is necessary. However, most diseases on leaves are visible to the naked eye and so a trained professional could tell what disease the leaf had and how to cure it. This is where the problem starts to occur as sometimes the professionals sent by the government or any organizations are amateur and could have more difficulties determining it than a professional plant pathologist. For this reason, an automated system is to be designed which can detect whether the leaf is diseased or not and if it is then what type of disease is it carrying. This booms the field of computer vision applications for precision agriculture. For this specific application, we explore the field of digital image processing and its common techniques such as feature detection. The feature detection was then used with the aim of detection and classification of plant diseases. For the classification, we used machine learning and convolutional neural networks.

Complete Chapter List

Search this Book:
Reset