scholarly journals Leaf Disease Classification using Advanced SVM Algorithm

2019 ◽  
Vol 8 (6S) ◽  
pp. 712-718
Keyword(s):  
Early Stage ◽  
Disease Classification ◽  
Green House ◽  
Leaf Disease ◽  
Svm Algorithm ◽  
Pest Detection ◽  
Color Conversion ◽  
System Focus

Presently there are many alternates of pesticides and unfortunately a very big portion of the industry is relies and using such poisons to protects crops to prevent from bugs attack and spreading of infection. Such pesticides are seriously very harmful and used unorganic chemicals. Even some of such pesticides are beneficial for insects too. Even some times there is also an possibility that such chemicals may be automatically washed during rain or watering the crops. So the research since years on green house agro system focus on early pest detection. Such methodology focus on observing plants by camera. The images captured by cameras can be used to analyzed that weather the plants are infected or not. A number of methods and algorithms such as color conversion, segmentation, k-mean, knn etc are used to classified such images. This research is focusing on the interpretation of image for early stage pest detection so that the crop should be prevented from damage.

scholarly journals Automatic Tomato Plant Leaf Disease Classification using Multi-Kernel Support Vector Machine

2020 ◽  
Vol 9 (5) ◽  
pp. 560-565
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Learning Algorithm ◽  
Early Stage ◽  
Region Of Interest ◽  
Input Image ◽  
Disease Classification ◽  
Support Vector ◽  
Leaf Disease ◽  
Kernel Support Vector Machine

In agriculture the major problem is leaf disease identifying these disease in early stage increases the yield. To reduce the loss identifying the various disease is very important. In this work , an efficient technique for identifying unhealthy tomato leaves using a machine learning algorithm is proposed. Support Vector Machines (SVM) is the methodology of machine learning , and have been successfully applied to a number of applications to identify region of interest, classify the region. The proposed algorithm has three main staggers, namely preprocessing, feature extraction and classification. In preprocessing, the images are converted to RGB and the average filter is used to eliminate the noise in the input image. After the pre-processing stage, features such as texture, color and shape are extracted from each image. Then, the extracted features are presented to the classifier to classify an input tomato leaf as a healthy or unhealthy image. For classification, in this paper, a multi-kernel support vector machine (MKSVM) is used. The performance of the proposed method is analysed on the basis of different metrics, such as accuracy, sensitivity and specificity. The images used in the test are collected from the plant village. The proposed method implemented in MATLAB.

Detection and Classification of Leaf Disease Using Deep Neural Network

2022 ◽  
pp. 51-77
Author(s):  
Meeradevi ◽  
Monica R. Mundada ◽  
Shilpa M.
Keyword(s):  
Neural Network ◽  
Plant Disease ◽  
Early Stage ◽  
Crop Productivity ◽  
Attention Mechanism ◽  
Disease Classification ◽  
Production Plant ◽  
Leaf Disease ◽  
Proposed Model

Modern technologies have improved their application in field of agriculture in order to improve production. Plant diseases are harmful to plant growth, which leads to reduced quality and quantity of crop. Early identification of plant disease will reduce the loss of the crop productivity. So, it is necessary to identify and diagnose the disease at an early stage before it spreads to the entire field. In this chapter, the proposed model uses VGG16 with attention mechanism for leaf disease classification. This model makes use of convolution neural network which consist of convolution block, max pool layer, and fully connected layer with softmax as an activation function. The proposed approach integrates CNN with attention mechanism to focus more on the diseased part of leaf and increase the classification accuracy. The proposed model design is a novel deep learning model to perform the fine tuning in the classification of nine different type of tomato plant disease.

scholarly journals Pest Detection in Plants Using Convolutional Neural Network

2021 ◽  
Vol 9 (11) ◽  
pp. 1583-1592
Author(s):  
Savita Sharma
Keyword(s):  
Artificial Intelligence ◽  
Image Processing ◽  
Climate Changes ◽  
Agricultural Sector ◽  
Predictive Analytics ◽  
Early Stage ◽  
Maximum Yield ◽  
Disease Classification ◽  
The World ◽  
Pest Detection

Abstract: Agriculture or farming is an imperative occupation since the historical backdrop of humanity is kept up. Artificial Intelligence is leading to a revolution in the agricultural practices. This revolution has safeguarded the crops from being affected by distinct factors like climate changes, porosity of the soil, availability of water, etc. The other factors that affect agriculture includes the increase in population, changes in the economy, issues related to food security, etc. Artificial Intelligence finds a lot of applications in the agricultural sector also which includes crop monitoring, soil management, pest detection, weed management and a lot more. Significant problems for sustainable farming include detection of illness and healthy monitoring of plants. Therefore, plant disease must automatically be detected with higher precision by means of image processing technology at an early stage. It consists of image capturing, preprocessing images, image segmentation, extraction of features and disease classification. The digital image processing method is one of those strong techniques used far earlier than human eyes could see to identify the tough symptoms. Considering different climatic situations in various regions of the world that impact local weather conditions. These climate changes affect crop yield directly. There is a great demand for such a platform in the world of today which would enable the farmer market his farm products. We have proposed in this study a system where farmers can sell their products directly to customers without the intervention of distributors and traders. The predictive analytics system is necessary for the farmer to get the maximum yield which benefit the farmer. This may be done if the environment, market conditions and knowledge of the timely planning of farms are known properly. Keywords: Pest Detection, Artificial Intelligence, Agriculture, Image processing, Convolutional Neural Networks

scholarly journals POS0140 URATE-LOWERING THERAPY REDUCES NON-EPISODIC FOOT PAIN IN PATIENTS WHO FAIL TO MEET ACR/EULAR 2015 GOUT CLASSIFICATION CRITERIA: AN EFFECT PREDICTED BY ULTRASOUND

2021 ◽  
Vol 80 (Suppl 1) ◽  
pp. 282.1-282
Author(s):  
R. Flood ◽  
C. Kirby ◽  
Y. Alammari ◽  
D. Kane ◽  
R. Mullan
Keyword(s):  
Early Stage ◽  
Serum Urate ◽  
Classification Criteria ◽  
Disease Classification ◽  
Foot Pain ◽  
Cross Sectional ◽  
Baseline Serum ◽  
First Metatarsophalangeal Joint ◽  
Lowering Therapy ◽  
Significant Difference

Background:Emerging evidence that the joints of asymptomatic hyperuricaemic individuals contain monosodium urate (MSU) deposits and that alternative presentations of foot pain occur in hyperuricaemia suggests that preclinical phases may occur prior to a first episodic gout attack. (1) This case–control study evaluates urate deposition in hyperuricaemic individuals not fulfilling the current gout classification criteria, as well as a potential therapeutic role for urate lowering therapy (ULT).Objectives:To investigate whether ULT reduces non-episodic foot pain in patients who fail to meet ACR/EULAR 2015 gout classification criteria.Methods:Following informed consent, hyperuricaemic individuals with persistent, non-episodic foot pain (n=53) not fulfilling ACR/EULAR 2015 gout classification criteria, were compared with asymptomatic hyperuricaemic controls (n=18). Ultrasound (US) of bilateral first metatarsophalangeal (MTP) joints and features of MSU deposition including double contour (DC) sign, tophus and juxta-articular erosion were recorded. Cases only were treated with febuxostat or allopurinol daily for 6 months. Serum urate, 24-hour and 7-day visual analogue score (VAS) 0–100 mm pain scales and the Manchester Foot Pain and Disability Index (MFPDI) were recorded before treatment and after 3 and 6 months. MTP Ultrasound was repeated after a minimum of 6 months on treatment.Results:53 hyperuricaemic individuals with persistent, non-episodic foot pain not meeting the ACR/EULAR 2015 gout classification criteria were recruited. At baseline MTP US DC sign, erosion and tophus occurred in 62.5%, 20.8% and 49% of cases, respectively. No US features of gout occurred in controls. No significant difference was seen in baseline serum urate between cases (481±14 mg/dL) versus controls (437±14; p=NS). Serum urate in cases fell at 3 months (325±25; p<0.01) and 6 months (248±19; p<0.01). For cases, baseline 24-hour pain VAS (46±3.9) reduced at 3 months (32±4.1; p<0.05) and 6 months (21±5.2; p<0.05) of ULT. The 7-day pain VAS (59±3.9) decreased at 3 months (35±4.5; p<0.05) and 6 months (30±5.3; P<0.05). MFPDI (17±1.4) decreased at 3 month (13±1.8; p=<0.05) and 6 months (11±2.2; p=<0.05). When cases were grouped according to the presence (N=33) or absence (N=18) of DC sign on baseline US, no differences were observed for baseline pain scores. Following ULT however, 24-hour pain VAS were significantly lower in DC positive patients at 3 months (22±4.48 DC positive vs 42±6.14 DC negative; p<0.05) and 6 months (12.±5.4 vs 33±8.4; p<0.05). The 7-day pain VAS were significantly lower in DC positive patients at 3 months (23±4.6 vs 47±6.6; p<0.05) and MFDPI were significantly lower in DC positive patients at 3 months (10±1.9 DC positive vs 19±2.9 DC negative; p<0.05).Conclusion:These findings indicate that persistent, non-episodic foot pain in hyperuricaemia is both associated with US features of MSU deposition and is responsive to ULT. Symptomatic hyperuricaemia occurring prior to episodic gout therefore represents an earlier or alternative disease presentation. Changes to the ACR/ EULAR classification criteria to include non-episodic foot pain in the presence of US features of gout may increase the sensitivity of disease classification at an early stage, leading to improved future treatment strategies and long-term outcomes.References:[1]Stewart S, Dalbeth N, Vandal AC, Rome K. Characteristics of the first metatarsophalangeal joint in gout and asymptomatic hyperuricaemia: A cross-sectional observational study. J Foot Ankle Res. 2015;8(1):1–8.Disclosure of Interests:None declared

Transfer Learning based Rice Leaf Disease Classification with Inception-V3

2021 ◽  
Author(s):  
Kotharu Uma Venkata Ravi Teja ◽  
Bhumula Pavan Venkat Reddy ◽  
Likhitha Reddy Kesara ◽  
Kotaru Drona Phani Kowshik ◽  
Lakshmi Anchitha Panchaparvala
Keyword(s):  
Transfer Learning ◽  
Disease Classification ◽  
Rice Leaf ◽  
Leaf Disease

scholarly journals Tomato Leaf Disease Detection Using Hybrid CNN-RNN Model

2021 ◽  
Author(s):  
Hepzibah Elizabeth David ◽  
K. Ramalakshmi ◽  
R. Venkatesan ◽  
G. Hemalatha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Early Stage ◽  
Computational Effort ◽  
Tomato Leaf ◽  
Disease Detection ◽  
Tomato Production ◽  
Classification Image ◽  
Leaf Disease ◽  
Learning Techniques

Tomato crops are infected with various diseases that impair tomato production. The recognition of the tomato leaf disease at an early stage protects the tomato crops from getting affected. In the present generation, the emerging deep learning techniques Convolutional Neural Network (CNNs), Recurrent Neural Network (RNNs), Long-Short Term Memory (LSTMs) has manifested significant progress in image classification, image identification, and Sequence Predictions. Thus by using these computer vision-based deep learning techniques, we developed a new method for automatic leaf disease detection. This proposed model is a robust technique for tomato leaf disease identification that gives accurate and better results than other traditional methods. Early tomato leaf disease detection is made possible by using the hybrid CNN-RNN architecture which utilizes less computational effort. In this paper, the required methods for implementing the disease recognition model with results are briefly explained. This paper also mentions the scope of developing more reliable and effective means of classifying and detecting all plant species.

Sign in / Sign up

Export Citation Format

Share Document