scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Rice Blast Disease Detection and Classification Using Machine Learning Algorithm

S. Ramesh1
01 Sep 2018-pp 255-259
TL;DR: A machine learning algorithm is proposed to find the symptoms of the disease in the rice plant using images taken from healthy and blast disease affected leaves using an automatic detection system.
Abstract: Rice blast disease is the major problem in all over the world of agriculture sector. The early detection of this disease will prevent the huge economic loss for the farmer. This paper proposes a machine learning algorithm to find the symptoms of the disease in the rice plant. Automatic detection of plant disease is carried out using machine learning algorithm. Images of healthy and blast disease affected leaves are taken for the proposed system. The features are extracted for the healthy and disease affected parts of the rice leaf. The total data set consists of 300 images and divided for training and testing purposes. These images are processed with the proposed method and the leaf is categorized as either infected or healthy. The simulation results provide an accuracy of 99% for the blast infected images and 100% for the normal images during the training phase. The testing phase accuracy is found to be 90% and 86% for the infected and healthy images respectively.
Citations
More filters
Journal ArticleDOI
TL;DR: A thorough investigation has been performed to evaluate the possibility of using Machine Learning models to identify plant diseases and various challenges in the use of machine learning and deep learning for plant disease detection and future research directions are enumerated and presented.
Abstract: Plant disease detection is a critical issue that needs to be focused on for productive agriculture and economy. Detecting plant disease using traditional methods is a tedious job as it requires a tremendous amount of work, time, and expertise. Automatic plant disease detection is an important research area that has recently gained a lot of attention among the academicians, researchers, and practitioners. Machine Learning and Deep Learning can help identify the plant disease at the initial stage as soon as it appears on plant leaves. In this state-of-an-art review, a thorough investigation has been performed to evaluate the possibility of using Machine Learning models to identify plant diseases. In this study, diseases and infections of four types of crops, i.e., Tomato, Rice, Potato, and Apple, are considered. Initially, numerous possible infections and diseases on these four kinds of crops are studied along with their reason for the occurrence and possible symptoms for their detections. An in-depth study of the different steps involved in plant disease detection and classification using Machine Learning and Deep Learning is provided. Various datasets available online for plant disease detection have also been presented. Along with this, a detailed study on various existing Machine Learning and Deep Learning-based classification models proposed by different researchers across the world for four considered crops in terms of their performance evaluations, the dataset used, and the feature extraction method is discussed. At last, various challenges in the use of machine learning and deep learning for plant disease detection and future research directions are enumerated and presented.

48 citations

Journal ArticleDOI
28 Aug 2022-Plants
TL;DR: This paper proposes a Deep Convolutional Neural Network transfer learning-based approach for the accurate detection and classification of rice leaf disease and achieves significantly better results compared with similar approaches using the same dataset or similar-size datasets reported in the extant literature.
Abstract: Rice is considered one the most important plants globally because it is a source of food for over half the world’s population. Like other plants, rice is susceptible to diseases that may affect the quantity and quality of produce. It sometimes results in anywhere between 20–40% crop loss production. Early detection of these diseases can positively affect the harvest, and thus farmers would have to be knowledgeable about the various disease and how to identify them visually. Even then, it is an impossible task for farmers to survey the vast farmlands on a daily basis. Even if this is possible, it becomes a costly task that will, in turn, increases the price of rice for consumers. Machine learning algorithms fitted to drone technology combined with the Internet of Things (IoT) can offer a solution to this problem. In this paper, we propose a Deep Convolutional Neural Network (DCNN) transfer learning-based approach for the accurate detection and classification of rice leaf disease. The modified proposed approach includes a modified VGG19-based transfer learning method. The proposed modified system can accurately detect and diagnose six distinct classes: healthy, narrow brown spot, leaf scald, leaf blast, brown spot, and bacterial leaf blight. The highest average accuracy is 96.08% using the non-normalized augmented dataset. The corresponding precision, recall, specificity, and F1-score were 0.9620, 0.9617, 0.9921, and 0.9616, respectively. The proposed modified approach achieved significantly better results compared with similar approaches using the same dataset or similar-size datasets reported in the extant literature.

22 citations

Proceedings ArticleDOI
19 Oct 2020
TL;DR: The results showed that the smartphone-based rice plant disease detection application functioned well, which was able to detect diseases in rice plants and improve the test accuracy value by adding the number of datasets and increasing the quality of the dataset.
Abstract: An increase in the human population requires an increase in agricultural production. Generally, the most important thing in agriculture that affects the quantity and quality of crops is plant diseases. In general, a farmer knows that his plant is attacked by a disease through direct vision. However, this process is sometimes inaccurate. With the development of machine learning technology, plant disease detection can be done automatically using deep learning. In this study, we report on a deep learning-based rice disease detection system that we have developed, which consists of a machine learning application on a cloud server and an application on a smartphone. The smartphone application functions to capture images of rice plant leaves, send them to the application on the cloud server, and receive classification results in the form of information on the types of plant diseases. The results showed that the smartphone-based rice plant disease detection application functioned well, which was able to detect diseases in rice plants. The performance of the rice plant disease detection system with VGG16 architecture has a train accuracy value of 100% and a test accuracy value of 60%. The test accuracy value can be improved by adding the number of datasets and increasing the quality of the dataset. It is hoped that with this system, rice plant disease control can be carried out appropriately so that yields will be maximized.

22 citations

Proceedings ArticleDOI
08 Apr 2021
TL;DR: In this article, an IoT based prototype system for surveillance is proposed that embeds the concept of multi-class classification technique using Machine and Deep Learning for the labels clear farm, horse, cow, wild elephant and wild boar.
Abstract: The IoT advancements have majorly influenced in redefining the agricultural field. A reliable remote monitoring system is the need of the hour. In this paper, two objectives are addressed. Firstly, an app based solution is presented which helps in displaying the current sensor values that efficiently aid in remotely administrating the field. Secondly, an IoT based prototype system for surveillance is proposed that embeds the concept of multi-class classification technique using Machine and Deep Learning for the labels clear farm, horse, cow, wild elephant and wild boar. Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) were analysed for this purpose and the best model was chosen based on accuracy metric.

14 citations

Proceedings ArticleDOI
21 Apr 2021
TL;DR: In this paper, a rice leaf disease detection system using a lightweight Artificial Intelligent technique using a Raspberry Pi has been presented, which is based on the edge computing concept and achieved 97.50% accuracy.
Abstract: Bangladesh is one of the top five rice-producing and consuming countries in the world. Its economy dramatically depends on rice-producing. Rice leaf disease is the biggest problem in the agriculture sector. This is the main reason for the reduction of the quality and quantity of the crops. The spread of the disease can be avoided by continuous monitoring. However, manual monitoring of diseases will cost a large amount of time and labor. So, it is a good idea to have an automated system. This paper presents a rice leaf disease detection system using a lightweight Artificial Intelligent technique. We are applying the edge computing concept here. Our edge device is Raspberry Pi. We have processed all our data in Raspberry Pi. We consider three rice plant diseases, namely Brown Spot, Hispa, and Leaf Blast. They are the most common type of rice leaf disease in Bangladesh. We have used clear images of healthy and infected rice leaves with white background. After applying the necessary preprocessing, we have extracted the necessary features from the images. Then we have made an image classification model with various machine learning algorithms by feeding these features. We have learned that the Random Forest algorithm performed the best. By using our image classification model, we have achieved 97.50% accuracy on our edge device.

12 citations

References
More filters
Book ChapterDOI
01 Jan 2012
TL;DR: This paper focuses on the analysis of the characteristics and mathematical theory of BP neural network and also points out the shortcomings of BP algorithm as well as several methods for improvement.
Abstract: The back propagation (BP) neural network algorithm is a multi-layer feedforward network trained according to error back propagation algorithm and is one of the most widely applied neural network models. BP network can be used to learn and store a great deal of mapping relations of input-output model, and no need to disclose in advance the mathematical equation that describes these mapping relations. Its learning rule is to adopt the steepest descent method in which the back propagation is used to regulate the weight value and threshold value of the network to achieve the minimum error sum of square. This paper focuses on the analysis of the characteristics and mathematical theory of BP neural network and also points out the shortcomings of BP algorithm as well as several methods for improvement.

433 citations


"Rice Blast Disease Detection and Cl..." refers background in this paper

  • ...The output layer provides the result of classification as normal and disease infected leaf image [6]....

    [...]

Proceedings ArticleDOI
01 Dec 2013
TL;DR: Effective algorithms for spread of disease and mango counting are demonstrated and artificial neural network concept is used for practical implementation using MATLAB.
Abstract: Due to the increasing demand in the agricultural industry, the need to effectively grow a plant and increase its yield is very important In order to do so, it is important to monitor the plant during its growth period, as well as, at the time of harvest In this paper image processing is used as a tool to monitor the diseases on fruits during farming, right from plantation to harvesting For this purpose artificial neural network concept is used Three diseases of grapes and two of apple have been selected The system uses two image databases, one for training of already stored disease images and the other for implementation of query images Back propagation concept is used for weight adjustment of training database The images are classified and mapped to their respective disease categories on basis of three feature vectors, namely, color, texture and morphology From these feature vectors morphology gives 90% correct result and it is more than other two feature vectors This paper demonstrates effective algorithms for spread of disease and mango counting Practical implementation of neural networks has been done using MATLAB

211 citations


"Rice Blast Disease Detection and Cl..." refers result in this paper

  • ...The morphology features provides 90% of the correctly results when compared to other two vectors [3]....

    [...]

Proceedings ArticleDOI
01 Apr 2017
TL;DR: In this paper, a Support Vector Machine based regression system for identification and classification of five cotton leaf diseases (Bacterial Blight, Alternaria, Gray Mildew, Cereospra, and Fusarium wilt) is proposed.
Abstract: Cotton is one of the most important cash crops in India. Every year the production of cotton is reducing due to the attack of the disease. Plant diseases are generally caused by pest insect and pathogens and decrease the productivity to large-scale if not controlled within time. This paper presents a system for detection and controlling of diseases on cotton leaf along with soil quality monitoring. The work proposes a Support Vector Machine based regression system for identification and classification of five cotton leaf diseases i.e. Bacterial Blight, Alternaria, Gray Mildew, Cereospra, and Fusarium wilt. After disease detection, the name of a disease with its remedies will be provided to the farmers using android app. The Android App is also used to display the soil parameters values such as humidity, moisture and temperature along with the water level in a tank. By using Android app farmers can ON/OFF the relay to control the motor and sprinkler assembly according to need. All this leaf disease detection system and sensors for soil quality monitoring are interfaced using Raspberry Pi which make it independent and cost effective system. The overall classification accuracy of this proposed system is 83.26%.

81 citations


"Rice Blast Disease Detection and Cl..." refers methods in this paper

  • ...The average color value of the image are calculated using this formula [2] Mean= E ∑ (1)...

    [...]

Proceedings ArticleDOI
01 Nov 2017
TL;DR: A computer vision based automatic system for the diagnosis of diseases caused by pests in the rice plants using genetic algorithm based feature selection approach and Artificial neural network and support vector machine is used for classification.
Abstract: One of the major reason behind degradation of quality and quantity of rice crop is pest. The lack of technical and scientific knowledge to prevent pest diseases is the main reason for low production of these commodities. This article aims to develop a computer vision based automatic system for the diagnosis of diseases caused by pests in the rice plants. Automatic disease detection using computer vision approach involves three types of feature extraction in this experiment. Diseased area of the leaf, textural descriptors using gray level co-occurrence matrix (GLCM) and color moments are extracted from diseased and non-diseased leaf images resulting in 21-D feature vector. Genetic algorithm based feature selection approach is employed to select relevant features and to discard redundant features, generating a 14-D feature vector that reduces the complexity. Artificial neural network (ANN) and support vector machine (SVM) is used for classification. The proposed algorithm results in classification accuracy of 92.5% using SVM and 87.5% using ANN.

52 citations


Additional excerpts

  • ...[5]....

    [...]

Proceedings ArticleDOI
28 Dec 2009
TL;DR: The result shows that the scheme is feasible to identify rice brown spot using image analysis and BP neural network classifier and the design was designed for classifying the healthy and diseased parts of rice leaves.
Abstract: Rice leaf diseases have occurred all over the world,including china.They have had a significant impact on rice quality and yield.Now,the control method rely mainly on artificial means.In this study,BP neural network classifiers were designed for classifying the healthy and diseased parts of rice leaves.This paper select rice brown spot as study object,the training and testing samples of the images are gathered from the northern part of Ningxia Hui Autonomous Region.The result shows that the scheme is feasible to identify rice brown spot using image analysis and BP neural network classifier. Keywords-rice brown spot;BP neuralnetwork;color feature;feature extraction

44 citations


"Rice Blast Disease Detection and Cl..." refers result in this paper

  • ...The results shows that the image analysis and BP neural networks are accurately detect the rice brown spot diseases [1]....

    [...]