Plant leaf disease detection using hybrid grasshopper optimization with modified artificial bee colony algorithm

The importance of plants is acknowledged because they provide the majority of human energy. due to their medicinal, nutritional, & other benefits. Any time during growing crops, plant diseases can affect the leaf, which can cause significant crop production losses and market value reduction. In...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications 2024-03, Vol.83 (8), p.22521-22543
Main Authors: Pavithra, P., Aishwarya, P.
Format: Article
Language:English
Subjects:
Ant colony optimization
Bees
Computer Communication Networks
Computer Science
Correlation coefficients
Crop production
Data Structures and Information Theory
Feature extraction
Grasshoppers
Market value
Methodology
Multimedia Information Systems
Optimization algorithms
Optimization techniques
Performance evaluation
Performance measurement
Plant diseases
Search algorithms
Special Purpose and Application-Based Systems
Swarm intelligence
Wiener filtering
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The importance of plants is acknowledged because they provide the majority of human energy. due to their medicinal, nutritional, & other benefits. Any time during growing crops, plant diseases can affect the leaf, which can cause significant crop production losses and market value reduction. In this paper, three optimization techniques are utilized to detect plant leaf disease. The input image has some noise signal which is removed by using the Modified Wiener Filter (MWF), this is the pre-processing stage of the proposed methodology. Feature Extraction is performed using Improved Ant Colony Optimization (IACO), this will extract the important features. The proposed model is described as Hybrid Grasshopper Optimization with a modified Artificial Bee Colony Algorithm (HyGmABC), which is used for classification. This will check whether the disease is present in the leaf region or not. The performance of the proposed methodology is evaluated using the performance metrics like accuracy, precision, recall, False Negative Ratio (FNR), Negative Prediction Value (NPV), and Matthews correlation coefficient (MCC). The plant village dataset is chosen for implementation. The proposed methodology produces high accuracy of 98.53% which is higher than the existing techniques.
ISSN:1573-7721
1380-7501
1573-7721
DOI:10.1007/s11042-023-16148-5