An Image Processing and Machine Learning Approach for Early Detection of Diseased Leaves

An Image Processing and Machine Learning Approach for Early Detection of Diseased Leaves

Sowmya B.J. (M.S. Ramaiah Institute of Technology, Bengaluru, India), Chetan Shetty (Ramaiah Institute of Technology, Bengaluru, India), Seema S. (Ramaiah Institute of Technology, Bengaluru, India) and Srinivasa K.G. (National Institute of Technical Teachers Training and Research, Chandigarh, India)
Copyright: © 2019 |Pages: 18
DOI: 10.4018/IJCPS.2019070104

Abstract

India is largely an agriculture dependent country. It contributes to almost 17% of the GDP. A wide range of crops are grown throughout the year. Extensive cultivation also makes the plants prone to a lot of diseases. There are no efficient methods to detect these diseases from its outset. People in the rural areas where most of the agriculture happens are totally helpless in situations where most of their crops have been affected by disease. Most of the diseases that plague plants leave a characteristic feature on the leaf. By applying image processing techniques like image enhancement and feature extraction one can extract the required information required to analyze the type and severity of the disease. The obtained information when fed to a classifier like support vector machine (SVM), the plant can be classified to be affected by a certain disease. One can also determine the stage of the disease (infant or mid or terminal). Crop diseases impact the livelihood of those involved in agriculture immensely. Consumption of such produce also affects the health of humans and animals. Manually monitoring these diseases requires a lot of time and expertise. Hence, utilizing image processing for the detection of diseases is a better option. It takes into consideration the features which may not be determined visually. Consider the example of tomato crop in India which is prone to a number of diseases caused by pathogens, bacteria, viruses, and phytoplasmas-like organisms. Due to this disease the framers incur a huge loss. To overcome this problem a lot research is being conducted using image processing and neural network model for automatic detection of diseases using drone technology.
Article Preview
Top

Introduction

As agriculture strives to satisfy the growing demands of today’s rapidly growing population, plant disease proves detrimental to the production as well as quality of crops. Losses can be disastrous or persistent, but a large proportion of crops are at stake of being damaged by a wide variety of diseases. Farmers spend a substantial sum of money on disease management, usually without adequate technical assistance, resulting in poor disease control, pollution and adverse effects. In addition, plant disease can lead to degradation of ecosystems, aggravating environmental loss caused by loss habitat loss and inferior land management. In a country like India, where environmental conditions are favorable, incomes are low and knowledge about investments in crop health management is minimal, the losses tends to be higher. Extreme crop losses can lead an entire community to adapt to imported foods and increase their dependency on processed foods disrupting their diet. Although, many farmers have been able to achieve good crop yield and efficient crop health management, some resource lacking farmers are still lagging behind in this concern. Therefore, an adept and economical methodology to detect these plant diseases is an imminent need. We, through this project envisage providing an efficient and precise method to detect a disease and its severity. Farmers could utilize our model to detect the onset of a disease and take necessary measures to stem the disease in its infancy, which would go a long in avoiding these diseases from affecting the plants in the first place. Agriculture constitutes about one-third of the workforce. This is a significant figure and hence failure in crop will incur huge loss. Failure in crops where pathogen, animals and weeds altogether are responsible range between 20-40% of the total agriculture productivity. Apart from monetary loss it has a tremendous impact on the society, among which the most significant was the Irish Famine (1845). It affected the country immensely and about 1.5 million people succumbed to this. Hence finding a way to detect and provide remedy for this issue is of utmost importance. At times when the human eye is not able to detect the plant disease precisely, tools such as image processing and classification render useful. Hence to deal with this issue we have built a system using Support Vector Machine (SVM) and neural network to classify the image and give remedies accordingly.

As India is fast developing country and agriculture is the backbone for the country’s development in the early stages. Due to industrialization and globalization, the field is facing hurdles. Moreover, agriculture constitutes approximately 1/3rd of the workforce all over the world. Diseases in plants lead to crop failure and hence farmers incur huge loss. In addition, this can degrade the quality of land and devastate the natural ecosystem. Farmers invest large amount of money in disease management without enough technological support.

In olden days identification is done manually by the experienced people but due to the so many environmental changes the prediction is becoming tough. Image processing techniques can be used for identification of plant disease. Early detection of disease in plants can lessen the risk of crop failure and increases yield. The reduced chances of diseases make the crop more nutritious and thereby decrease health issues for consumers. For this project we use tomato crop as an example for implementing the method.

Tomato is one of the most caring food crops of India. The tomato crop is cultivated in all the seasons but typically during winter and summer seasons. Temperature and light intensity affect the pigmentation, fruit-sets and nutritive value of the fruits. Due to all these environments plant become very susceptible to diseases caused by fungi, bacteria, and viruses. Early detection can immensely help prevent diseases thereby increasing yield.

An application which correctly detects the disease given the image of tomato leaf helps farmers take necessary measures.

The objectives are:

  • Implementation of leaf disease detection using SVM and Alexnet.

  • The implemented system must be able to perform classification correctly.

  • Provide solution with least hardware requirement.

  • To apply image processing technique to analyze the pattern of tomato leaf disease.

The paper is organized as literature survey in the 2nd section, design and implementation as the 3rd section, results in the 4th section, and then the conclusion.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 2: 2 Issues (2020): Forthcoming, Available for Pre-Order
Volume 1: 2 Issues (2019)
View Complete Journal Contents Listing