Only on Eduzaurus

Identification of Plant Disease Using Machine Learning Approach

Download essay
Need help with writing assignment?
writers online
to help you with essay
Download PDF

A Survey Paper on Plant Disease “Identification Using Machine Learning Approach”

Department of Computer Science and Engineering, Sanjay Ghodawat Institutes, Atigre, India


Agriculture plays an important role in farmer’s life. Sometimes manual identification of disease is time consuming and need of labor is more. One of the most important fact that reduces the growth of plants is disease attack. Many studies show that quality of agricultural products may be reduced due to various factors of plant diseases. These disease can be more easily identified by using machine learning approach as compared to manual method. Hence machine learning method can be used to identify the affected leaf images. The images required for this work are captured using drone camera as drone camera can conquer the big fields. The captured images are then processed on system using feature extraction and image processing techniques. These techniques will help in identifying plant diseases thereby increasing the yield of plants. This survey paper on plant disease identification using Machine Learning Approach. Summary of various techniques for disease identification and classification is also done.Keywords: Feature extraction, image processing techniques, SVM, PNN, MSOFM and GAI.

Essay due? We'll write it for you!

Any subject

Min. 3-hour delivery

Pay if satisfied

Get your price


Agriculture is one of the important source of income for farmer. Farmers can grow variety of plants but diseases hamper the growth of plants. One of the major factors that leads the destruction of plant is disease attack. Disease attack may reduce the productivity plants from 10%-95%. At present there are different strategies to get rid of plant diseases such as removing the affected plants manually, mechanical cultivation and last is using different pesticides. The easy method to detect to plant disease is taking help of agricultural expert. But this method of manual detection of diseases takes lot of time and is laborious work. Next method is using pesticide but excess use of pesticide may increase growth of plants but it reduces the quality of plant. But using more pesticide for plants without analyzing how much quantity of pesticide is needed for particular crop because excess use of pesticide may lead adverse effect on environment and human health.

Classification of Plant and Diseased Plants using digital image processing and Machine Learning approach which can help to control growth of diseases on Plants using the pesticides in the quantity needed so that excess use of pesticides can be avoided. Automatic identification of plant diseases is an important task as it may be proved beneficial for farmer to monitor large field of plants ,and identify the disease using machine learning approach .As compared to image processing technique using machine learning approach manual disease identification is less accurate and time consuming.

Literature Survey

In order to know about the previous research work done in this direction, several studies dedicated to the topic were referred. The literature survey is done in chronological order from 2012-2016.F Ahmed in 2012, [1] has stated that in most agricultural systems, one of the major concerns is to reduce the growth of Unwanted Plants .In most cases, removal of the Unwanted Plants population in agricultural fields involves the application of chemical herbicides, which may lead to huge productivity but adverse effect on environment and human health. The ability of locating and classifying plants and Unwanted Plants in digital images could lead to development of autonomous vision guided agricultural equipment’s for site-specific herbicide application.

Suhaili Beeran Kutty in 2013, [2] have considered an artificial neural network (ANN) based system to classify the watermelon leaf diseases of Downney Mildew and Anthracnose .This classification is based on the color feature extraction from RGB color model which is obtained from the identified pixels in the region of interest. Result of this work showed that the leaf disease achieved 75.9% of accuracy based on its RGB color componentGodliver Owomugisha in 2014, has stated that Machine learning is one of the approach which has been applied in Agriculture but also in other fields including crop disease detection for some crops. No machine learning techniques has been used to detect banana plant such as banana bacterial wilt (BBW) and etc.

There are various computer vision techniques which led to the development of an algorithm that consists of three main phases:

  1. The images of banana leaves where acquired using a standard digital camera.
  2. It involves use of different feature extraction techniques to obtain relevant data to be used.
  3. where images are classified as either healthy or diseased.

Extremely randomized trees performed best in identifying the diseases achieving 0.96 AUC for BBW and 0.91 for BBS.Mrunmayee Dhakte in 2015, has stated that Pomegranate is the one of the fruit grown in large quantity in many states of India and one of the most profit gaining fruit. But due to various reasons plants are infected by various diseases which destroys the crop. The work proposes an image processing and neural network methods to deal with main issues of phytopathology. In this system GLCM feature extraction techniques and k-means machine learning approach are used. Accuracy of this system to detect disease is 90%.Arti Singh in 2016, has stated that Advances in automated and high throughput images has resulted in deluge of high-resolution images and sensor data of plants. Extracting patterns and features from this set of data requires the use of machine learning techniques to find out data assimilation and feature identification.

Different steps in which machine learning approaches can be deployed are Identification, classification, quantification and prediction.Sharada P.Mohanty in 2016, has stated that crop diseases are the main threat to food security, but their rapid detection remains difficult in many parts of the world due to lack of required infrastructure. The combination of increasing global use of smartphone and recent advances in computer advances made possible by deep learning has paved the way for smartphone assisted disease diagnosis. The trained model achieves 99.35% accuracy.

Machine Learning Approaches

Machine learning is field of computer science that uses statistical techniques to give computer system the ability to “learn” with data, without being explicitly programmed. Decision tree learning uses a decision tree as a predictive model, which maps observations about an item to conclusions about the items target value. Association rule learning is a method for discovering inter-esting relations between variables in large database.

Artificial Neural Network

Artificial Neural Network (ANN) also called as neural networks inspired by biological neural networks. Computations are structured in terms of an interconnected group of artificial neurons, processing information using a connectionist approach to computation.DT comprises a set of ‘rules’ that provide the means to associate specific molecular features and/or descriptor values with the activity or property of interest. The DT approach has been applied to problems such as designing combinatorial libraries, predicting ‘drug-likeness’, predicting specific biological activities, and generating some specific compound profiling data.upport Vector Machines: Support Vector Machines (SVMs) are set of related supervising methods used for classification and regression. Given a set of training examples, each marked as belonging to one of two categories, an SVM training algorithm builds a model that predicts whether a new example falls into one category or the other.


Cluster analysis is the assignment of a set of observations into subsets (called clusters) so that observations within the same cluster are similar according to some predesignated criterion or criteria, while observations drawn from different clusters are different.3.5 k-Nearest Neighbor: k-Nearest Neighbor is a simple classifier in the machine learning techniques where the classification is achieved by identifying the nearest neighbors to query examples and then make use of those neighbors for determination of the class of query.

Genetic Algorithm

A genetic algorithm (GA) is a search heuristic that mimics the process of natural selection, and uses methods such as mutation and crossover to generate new genotype in the hope of finding good solutions to a given problem.


The survey of different papers have given different identification and classification techniques which have been summarized above. As per the survey, this paper has made an attempt to study machine learning method used by researchers to identify diseases and classification. These machine learning methods will help system to identify disease occurred on plant by image processing and system will inform farmer about disease in detail and specify the medicine to get rid of plant disease and increase the productivity of plants.


  1. F Ahmed, HA AI-Mamun, ASMH Bari, E Hossain, “Classification of crops and weeds from digital images: A SVM approach”, Elsevier-2012.
  2. Suhaili Beeran Kutty, Noor Ezan Abdullah, Dr. Hadzli Hashim, A’zraa Afhzan Ab Rahim, Aida.


This essay has been submitted by a student. This is not an example of the work written by our professional essay writers. You can order our professional work here.

We use cookies to offer you the best experience. By continuing, we’ll assume you agree with our Cookies policy.

Want to get a custom essay from scratch?

Do not miss your deadline waiting for inspiration!

Our writers will handle essay of any difficulty in no time.