scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Vegetable Disease Detection Using K-Means Clustering And Svm

06 Mar 2020-pp 1308-1311
TL;DR: A vegetable disease detection system for recognizing diseased vegetables based on features with K-means clustering algorithm and a recognition system for 2D input images is proposed.
Abstract: India is the cultivating country and our country is the biggest maker in agricultural products. So, we have to classify and exchange our agricultural products. Manual arranging is tedious and it requires works. The automatic grading system requires less time for grading of the agricultural products. Image processing technique is helpful in examination and evaluating the products. In this paper we proposed a vegetable disease detection system for recognizing diseased vegetables. Here we utilize the Image processing system for reviewing the vegetables. Vegetables are recognized dependent on their features. The features are color, shape, size, texture. We extract these features utilizing algorithms to distinguish the vegetables. We develop a recognition system for 2D input images. The main aim of this work is detecting infected vegetable based on features with K-means clustering algorithm. Algorithm includes three main steps namely enhancement, segmentation and classification. Vegetable samples are collected as images from high resolution camera and data acquisition is carried out for database preparation. The image segmentation process is based on pixel of the image and is applied to get the segmented and infected vegetables using K-Means Clustering algorithm. The image classification is based on Support Vector Machine (SVM) which perform supervised leaning for classification.
Citations
More filters
Journal ArticleDOI
TL;DR: In this article , a new method is proposed using BO (BO)-based MobilNetv2, ResNet-50 models, SVM and kNN machine learning algorithms for the diagnosis of COVID-19 with CT scans.
Abstract: Early diagnosis of COVID-19, the new coronavirus disease, is considered important for the treatment and control of this disease. The diagnosis of COVID-19 is based on two basic approaches of laboratory and chest radiography, and there has been a significant increase in studies performed in recent months by using chest computed tomography (CT) scans and artificial intelligence techniques. Classification of patient CT scans results in a serious loss of radiology professionals' valuable time. Considering the rapid increase in COVID-19 infections, in order to automate the analysis of CT scans and minimize this loss of time, in this paper a new method is proposed using BO (BO)-based MobilNetv2, ResNet-50 models, SVM and kNN machine learning algorithms. In this method, an accuracy of 99.37% was achieved with an average precision of 99.38%, 99.36% recall and 99.37% F-score on datasets containing COVID and non-COVID classes. When we examine the performance results of the proposed method, it is predicted that it can be used as a decision support mechanism with high classification success for the diagnosis of COVID-19 with CT scans.

11 citations

Journal ArticleDOI
TL;DR: Three hybrid memetic approaches between K-Means and GSO are presented, named FMK GSO, MKGSO and TMKGSO, in such a way that the global search capabilities of GSO is combined with the fast local search performances of K- means.
Abstract: Cluster analysis is one important field in pattern recognition and machine learning, consisting in an attempt to distribute a set of data patterns into groups, considering only the inner properties of those data. One of the most popular techniques for data clustering is the K-Means algorithm, due to its simplicity and easy implementation. But K-Means is strongly dependent on the initial point of the search, what may lead to suboptima (local optima) solutions. In the past few decades, Evolutionary Algorithms (EAs), like Group Search Optimization (GSO), have been adapted to the context of cluster analysis, given their global search capabilities and flexibility to deal with hard optimization problems. However, given their stochastic nature, EAs may be slower to converge in comparison to traditional clustering models (like K-Means). In this work, three hybrid memetic approaches between K-Means and GSO are presented, named FMKGSO, MKGSO and TMKGSO, in such a way that the global search capabilities of GSO are combined with the fast local search performances of K-Means. The degree of influence of K-Means on the behavior of GSO method is evaluated by a set of experiments considering both real-world problems and synthetic data sets, using five clustering metrics to access how good and robust the proposed hybrid memetic models are.

10 citations

Proceedings ArticleDOI
08 Apr 2021
TL;DR: In this article, the histogram features (statistical feature) are extracted for further recognition of wheat rust diseased images, which is a good approach to enhance the pixel intensity of an image.
Abstract: In the agriculture domain, wheat is the most important crop across the world. It is a winter cereal crop that provides 14% food production worldwide. Wheat is an essential food for everyone. The motivation behind this work is to enhance the quality of wheat crop images in the agricultural area. Sometimes, the pictures captured in a real-time environment may not be clear for detecting the disease from the crop. So, there is a need to enhance the images. In this paper, histogram features (statistical feature) are extracted for further recognition of wheat rust diseased images. The histogram equalization is a good approach to enhance the pixel intensity of an image. Moreover, various challenges to enhance the quality of an image have also been explored, such as the effect of the histogram, histogram equalization, and Contrast Limited Adaptive Histogram Equalization (CLAHE). Also, it is observed that instead of plotting a simple histogram, histogram equalization is the best way to equalize all pixel values at the same level. In addition to that, various color spaces models such as RGB and HSV have been utilized for analysis. Thereafter, the importance of a 3D plot for color distribution is also discussed. It is concluded that histogram equalization really helps in enhancing the quality of the image and also using 3D plots one can get fine information to estimate the majority of different colors present in the image for performing segmentation and feature extraction.

7 citations

Journal ArticleDOI
TL;DR: In this paper , the authors used K-Means clustering and Support Vector Machine Algorithm in MATLAB to detect and distinguish different types of leaf and skin diseases in agricultural images.
Abstract: Agricultural production is something on which the economy significantly relies. Leaf diseases in agriculture are the key issue for every nation, as the food demand is expanding at a rapid speed due to a rise in population. Skin disorders are usually seen in animals and humans, it is a particular sort of illness caused by germs or infection. Early and accurate identification and diagnosis of leaf and skin diseases are vital to keeping them from spreading. Image processing techniques can be used for disease detection which involves mathematical equations and mathematical transformations. For humans eyes image is a mixture of RGB colour, because of these colours we can extract some of the features from the image, but modern computer stores image in a mathematical format which means computer sees the image as numbers, hence after evaluating the image as a number arrays or matrix we will perform various transforms on them, these transforms will extract specific details from the picture, before transforming the image must go under various operation like feature adjustment which is also carried out mathematically. The project is implemented using K-Means Clustering and Support Vector Machine Algorithm in MATLAB through which we can detect and distinguish different types of leaf and skin diseases.

7 citations

Journal ArticleDOI
TL;DR: In this article, an automated machine learning-based algorithm is proposed for the detection of type and quality grading of five different (jalapeno, lemon, sweet potato, cabbage, and tomato) vegetables and four different (apple, avocado, banana, and orange) varieties of fruits.
Abstract: Vegetable and fruit security plays a crucial role in the Indian economy. In the recent past, it has been noted that vegetables and fruits are affected by different diseases. This leads to the failure of the economy in the agriculture field. The identification of type and grading of vegetables and fruit is onerous due to the heavy production of products. The manual investigation is expensive, laborious, and inconsistent. Thus, an automated machine learning–based algorithm is proposed for the detection of type and quality grading of five different (jalapeno, lemon, sweet potato, cabbage, and tomato) vegetables and four different (apple, avocado, banana, and orange) varieties of fruits. Firstly, images are preprocessed by Gaussian filtering to enhance the quality of the image and removing of noise. Secondly, segmentation of images is done by fuzzy c-means clustering and grab-cut. Then, various features, namely, statistical, color, textural, geometrical, Laws’ texture energy, the histogram of gradients, and discrete wavelet transform, are extracted (114) and selected from feature vector by PCA. The detection of vegetable and fruit types is done by color and geometrical features while all other features are considered for grading. Lastly, LR, SRC, ANN, and SVM are used to make decisions for sorting and grading. The performance of the system has been validated by the k (10) fold cross-validation technique. The proposed algorithm achieves 85.49% (LR), 87.63% (SRC), 92.64% (ANN), and 97.63% (SVM) for detection of type. Also, the system achieves 83.91% (LR), 85.00% (SRC), 89.54% (ANN), and 96.59% (SVM) for grading. The proper feature selection shows the enhanced performance of the system. Among four different classifiers, SVM shows more efficient results that are promising and comparable with the literature.

7 citations

References
More filters
01 Jan 2010
TL;DR: An efficient fusion of color and texture features for fruit recognition is proposed based upon the statistical and co-occurrence features derived from the Wavelet transformed sub- bands.
Abstract: The computer vision strategies used to recognize a fruit rely on four basic features which characterize the object: intensity, color, shape and texture. This paper proposes an efficient fusion of color and texture features for fruit recognition. The recognition is done by the minimum distance classifier based upon the statistical and co-occurrence features derived from the Wavelet transformed sub- bands. Experimental results on a database of about 2635 fruits from 15 different classes confirm the effectiveness of the proposed approach.

159 citations

Journal ArticleDOI
TL;DR: The fruit detection using improved multiple features based algorithm is presented, which can be applied for targeting fruits for robotic fruit harvesting.
Abstract: icient locating the fruit on the tree is one of the major requirements for the fruit harvesting system. This paper presents the fruit detection using improved multiple features based algorithm. To detect the fruit, an image processing algorithm is trained for efficient feature extraction. The algorithm is designed with the aim of calculating different weights for features like intensity, color, orientation and edge of the input test image. The weights of different features represent the approximate locations of the fruit within an image. The Detection Efficiency is achieved up to 90% for different fruit image on tree, captured at different positions. The input images are the section of tree image. The proposed approach can be applied for targeting fruits for robotic fruit harvesting.

102 citations


Additional excerpts

  • ...[6] introduced the fruit, an image processing technique is ready for proficient component extraction....

    [...]

01 Jan 2012
TL;DR: The developed system utilizes image-processing techniques to classify and grade fruits using Fuzzy Logic approach and the results obtained are very promising.
Abstract: Now a days, the classification and grading is performed based on observations and through experience. The system utilizes image-processing techniques to classify and grade fruits. The developed system starts the process by capturing the fruit's image using a regular digital camera. Then, the image is transmitted to the processing level where feature extraction, classification and grading is done using MATLAB. The fruits are classified based on color and graded based on size. Both classification and grading are realized by Fuzzy Logic approach. The results obtained are very promising.

30 citations

DOI
28 Jul 2015
TL;DR: In this proposed paper neural network is used to detect shape, size and colour of fruit and with the combination of these three features the results obtained are very promising.
Abstract: Grading and classification of fruits is based on observations and through experiences. The system utilizes image-processing techniques to classify and grade quality of fruits. Two dimensional fruit images are classified on shape and colour based analysis methods. However, different fruit images may have similar or identical colour and shape values. Hence, using colour or shape features analysis methods are still not effective enough to identify and distinguish fruits images. Therefore, we used a method to increase the accuracy of the fruit quality detection by using colour, shape, and size based method with combination of artificial neural network (ANN). Proposed method grades and classifies fruit images based on obtained feature values by using cascaded forward network. The proposed system starts the process by capturing the fruit’s image. Then, the image is transmitted to the processing level where the fruit features like colour, shape and size of fruit samples are extracted. After that by using artificial neural network fruit images are going through the training and testing. In this proposed paper neural network is used to detect shape, size and colour of fruit and with the combination of these three features the results obtained are very promising. .

22 citations


"Vegetable Disease Detection Using K..." refers background in this paper

  • ...MandeepKaur, Reecha Sharma,Quality Detection of Fruits by Using ANN Technique, IOSR Journal of Electronics and Communication Engineering, Volume 10, Issue 4, 2015....

    [...]

  • ...in the given below Figre[1] first part is training part and second part is testing part(2)....

    [...]

  • ...Mandeep Kaur, Reecha Sharma [1], during this paper they detect the standard of the image by extracting features....

    [...]

  • ...IN Sixth phase it will recognize which disease is infected for that image.in the given below Figre[1] first part is training part and second part is testing part(2)....

    [...]

Journal Article
TL;DR: In this paper, three general models were established; single and multiple variable regressions of tomato dimensions and projected areas, and modeling tomato mass based on its measured volume and mass, which revealed that mass can be best modeled on the basis of intermediate diameter.
Abstract: There are instances in which it is desirable to determine relationship between various physical characteristics of vegetables and fruits. Although vegetables and fruitsare often graded on the basis of size and projected area, it may be more economical to develop a machine which would grade by produce mass. Therefore, relationships of mass with other physical characteristics are needed. In this study, Market King variety of tomato was selected and fruit dimensions and projected area were used to develop a number of models for predicting mass of tomato. Three general models were established;Single and multiple variable regressions of tomato dimensions, single and multiple variable regressions of projected areas andmodeling tomato mass based on its measured volume and mass.Results revealed that for the first modelthat mass can be best modeled on the basis of intermediate diameter.Results for model #2show thatmodel based on 2 nd projected area is a preferredmodel for mass.The third model which isbased onellipsoid volumecan estimate tomato mass satisfactorily( ). This study

6 citations


"Vegetable Disease Detection Using K..." refers background in this paper

  • ...HadiIzadietal[3], determined the relationships between fruits and vegetables based on size and projected area of single and multiple dimensions....

    [...]