View in EDS

A Crayfish Optimization Algorithm with a Random Perturbation Strategy and Removal Similarity Operation for Color Image Enhancement

Saved in:
Bibliographic Details
Title: A Crayfish Optimization Algorithm with a Random Perturbation Strategy and Removal Similarity Operation for Color Image Enhancement
Authors: Jiquan Wang, Min Wang, Haohao Song, Jinling Bei
Source: Agriculture ; Volume 16 ; Issue 3 ; Pages: 364
Publisher Information: Multidisciplinary Digital Publishing Institute
Publication Year: 2026
Collection: MDPI Open Access Publishing
Subject Terms: crayfish optimization algorithm, color image enhancement, remove similarity, random perturbation strategy, agricultural pests and diseases
Subject Geographic: agris
Description: Image enhancement can effectively improve the contrast, clarity, and information content of images, thereby improving visual quality. Image enhancement has significant application value in the process of identifying and diagnosing agricultural pests and diseases. This paper proposes a color image enhancement method based on color space transformation, converting the image from the RGB space to the HSV space, conducting targeted enhancement on the V channel, and combining adaptive brightness adjustment and Gamma correction to further improve the visual effect. To achieve better enhancement results, this paper designs a crayfish optimization algorithm with a random perturbation strategy and removal similarity operation (COA-RPRS). This algorithm achieves a dynamic balance between exploration and exploitation through an adaptive temperature calculation formula and improves the position update mechanism in the summer escape, competition, and foraging stages, significantly enhancing convergence performance. Moreover, introducing a removal similarity operation and a random perturbation strategy based on Lévy flight effectively maintains population diversity and prevents premature convergence. Experimental verification was conducted on the CEC 2017 test functions, 20 color images, and 10 images of rice pests and diseases, showing that COA-RPRS achieves superior performance compared to eight other comparison algorithms in both global optimization and color image enhancement tasks. These results suggest its potential applicability in supporting intelligent recognition and diagnostic systems for agricultural pest and disease management.
Document Type: text
File Description: application/pdf
Language: English
Relation: Artificial Intelligence and Digital Agriculture; https://dx.doi.org/10.3390/agriculture16030364
DOI: 10.3390/agriculture16030364
Availability: https://doi.org/10.3390/agriculture16030364
Rights: https://creativecommons.org/licenses/by/4.0/
Accession Number: edsbas.F7A8ADD0
Database: BASE
Description
Abstract:Image enhancement can effectively improve the contrast, clarity, and information content of images, thereby improving visual quality. Image enhancement has significant application value in the process of identifying and diagnosing agricultural pests and diseases. This paper proposes a color image enhancement method based on color space transformation, converting the image from the RGB space to the HSV space, conducting targeted enhancement on the V channel, and combining adaptive brightness adjustment and Gamma correction to further improve the visual effect. To achieve better enhancement results, this paper designs a crayfish optimization algorithm with a random perturbation strategy and removal similarity operation (COA-RPRS). This algorithm achieves a dynamic balance between exploration and exploitation through an adaptive temperature calculation formula and improves the position update mechanism in the summer escape, competition, and foraging stages, significantly enhancing convergence performance. Moreover, introducing a removal similarity operation and a random perturbation strategy based on Lévy flight effectively maintains population diversity and prevents premature convergence. Experimental verification was conducted on the CEC 2017 test functions, 20 color images, and 10 images of rice pests and diseases, showing that COA-RPRS achieves superior performance compared to eight other comparison algorithms in both global optimization and color image enhancement tasks. These results suggest its potential applicability in supporting intelligent recognition and diagnostic systems for agricultural pest and disease management.
DOI:10.3390/agriculture16030364