A Perspective View of Cotton Leaf Image Classification Using Machine Learning Algorithms Using WEKA

Cotton is one of the major crops in India, where 23% of cotton gets exported to other countries. The cotton yield depends on crop growth, and it gets affected by diseases. In this paper, cotton disease classification is performed using different machine learning algorithms. For this research, the co...

Full description

Saved in:
Bibliographic Details
Published in:Advances in human-computer interaction Vol. 2021; pp. 1 - 15
Main Authors: Patil, Bhagya M., Burkpalli, Vishwanath
Format: Journal Article
Language:English
Published: New York Hindawi 2021
John Wiley & Sons, Inc
Wiley
Subjects:
Accuracy
Agricultural production
Algorithms
Analysis
Bayesian analysis
Classification
Classifiers
Color
Corn
Correlation coefficient
Correlation coefficients
Cotton
Cotton industry
Crop diseases
Crop growth
Crop yield
Crop yields
Data mining
Datasets
Decision trees
Experimentation
Feature extraction
Image classification
Image segmentation
Learning algorithms
Leaves
Machine learning
Medical imaging
Multilayer perceptrons
Neural networks
Optimization algorithms
Performance evaluation
Plant diseases
Skin cancer
Support vector machines
Texture
Germany
India
ISSN:1687-5893, 1687-5907
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Cotton is one of the major crops in India, where 23% of cotton gets exported to other countries. The cotton yield depends on crop growth, and it gets affected by diseases. In this paper, cotton disease classification is performed using different machine learning algorithms. For this research, the cotton leaf image database was used to segment the images from the natural background using modified factorization-based active contour method. First, the color and texture features are extracted from segmented images. Later, it has to be fed to the machine learning algorithms such as multilayer perceptron, support vector machine, Naïve Bayes, Random Forest, AdaBoost, and K-nearest neighbor. Four color features and eight texture features were extracted, and experimentation was done using three cases: (1) only color features, (2) only texture features, and (3) both color and texture features. The performance of classifiers was better when color features are extracted compared to texture feature extraction. The color features are enough to classify the healthy and unhealthy cotton leaf images. The performance of the classifiers was evaluated using performance parameters such as precision, recall, F-measure, and Matthews correlation coefficient. The accuracies of classifiers such as support vector machine, Naïve Bayes, Random Forest, AdaBoost, and K-nearest neighbor are 93.38%, 90.91%, 95.86%, 92.56%, and 94.21%, respectively, whereas that of the multilayer perceptron classifier is 96.69%.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1687-5893
1687-5907
DOI:10.1155/2021/9367778