Smart adaptive learning and optimized feature clustering for enhanced image retrieval

Abstract In recent years, Content-Based Image Retrieval (CBIR) has faced increasing challenges due to the rapid growth of multimedia content on the Internet. One of the primary difficulties in CBIR lies in identifying dissimilarities between various objects. This paper introduces a novel approach ca...

Full description

Saved in:
Bibliographic Details
Main Authors: P. Umaeswari, Sujata Patil, Parameshachari Bidare Divakarachari, Przemysław Falkowski-Gilski
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-10375-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343871415222272
author P. Umaeswari
Sujata Patil
Parameshachari Bidare Divakarachari
Przemysław Falkowski-Gilski
author_facet P. Umaeswari
Sujata Patil
Parameshachari Bidare Divakarachari
Przemysław Falkowski-Gilski
author_sort P. Umaeswari
collection DOAJ
description Abstract In recent years, Content-Based Image Retrieval (CBIR) has faced increasing challenges due to the rapid growth of multimedia content on the Internet. One of the primary difficulties in CBIR lies in identifying dissimilarities between various objects. This paper introduces a novel approach called SEGJO (Scaling Factor and Elite Opposition Learning-based Golden Jackal Optimization) for effective clustering of extracted features in CBIR. The inclusion of a Scaling Factor (SF) and Elite Opposition Learning (EOL) in SEGJO enhances its search capabilities and helps prevent premature convergence during the clustering process. CBIR extracts key features related to texture, shape, and color using techniques such as Local Binary Pattern, Zernike Moments, and Color Moments. Additionally, an Entropy-based Divergence (ED) function is incorporated into a Convolutional Neural Network (CNN) named EDCNN to improve matching accuracy by reducing redundant activation in hidden layers. The proposed SEGJO-EDCNN method is evaluated on the Corel 5 K and Oxford Flower datasets, and its performance is measured using precision, recall, F-score, mean average precision, and average recall. Comparative analysis with existing methods—ELNDP, SVM-CBIR, SPDNN, and DNN-SAR—demonstrates that SEGJO-EDCNN achieves a higher mean average precision of 97.595% on the Corel 5 K dataset, outperforming both ELNDP and DNN-SAR. Next, the MAP of SEGJO-EDCNN for the Oxford flower dataset is 99.239% which is higher compared to the SVM-CBIR.
format Article
id doaj-art-3bd2cc1b7e044d73a5cbf152230340db
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-3bd2cc1b7e044d73a5cbf152230340db2025-08-20T03:42:49ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-10375-6Smart adaptive learning and optimized feature clustering for enhanced image retrievalP. Umaeswari0Sujata Patil1Parameshachari Bidare Divakarachari2Przemysław Falkowski-Gilski3Department of Computer Science and Business Systems R.M.K. Engineering CollegeDepartment of Electronics and Communication, KLE Technological UniversityDepartment of Electronics and Communication Engineering, Nitte Meenakshi Institute of TechnologyFaculty of Electronics, Telecommunications and Informatics, Gdansk University of TechnologyAbstract In recent years, Content-Based Image Retrieval (CBIR) has faced increasing challenges due to the rapid growth of multimedia content on the Internet. One of the primary difficulties in CBIR lies in identifying dissimilarities between various objects. This paper introduces a novel approach called SEGJO (Scaling Factor and Elite Opposition Learning-based Golden Jackal Optimization) for effective clustering of extracted features in CBIR. The inclusion of a Scaling Factor (SF) and Elite Opposition Learning (EOL) in SEGJO enhances its search capabilities and helps prevent premature convergence during the clustering process. CBIR extracts key features related to texture, shape, and color using techniques such as Local Binary Pattern, Zernike Moments, and Color Moments. Additionally, an Entropy-based Divergence (ED) function is incorporated into a Convolutional Neural Network (CNN) named EDCNN to improve matching accuracy by reducing redundant activation in hidden layers. The proposed SEGJO-EDCNN method is evaluated on the Corel 5 K and Oxford Flower datasets, and its performance is measured using precision, recall, F-score, mean average precision, and average recall. Comparative analysis with existing methods—ELNDP, SVM-CBIR, SPDNN, and DNN-SAR—demonstrates that SEGJO-EDCNN achieves a higher mean average precision of 97.595% on the Corel 5 K dataset, outperforming both ELNDP and DNN-SAR. Next, the MAP of SEGJO-EDCNN for the Oxford flower dataset is 99.239% which is higher compared to the SVM-CBIR.https://doi.org/10.1038/s41598-025-10375-6Content-Based image retrievalConvolutional neural networkElite opposition learningEntropy-based divergence functionGolden Jackal optimizationScaling factor
spellingShingle P. Umaeswari
Sujata Patil
Parameshachari Bidare Divakarachari
Przemysław Falkowski-Gilski
Smart adaptive learning and optimized feature clustering for enhanced image retrieval
Scientific Reports
Content-Based image retrieval
Convolutional neural network
Elite opposition learning
Entropy-based divergence function
Golden Jackal optimization
Scaling factor
title Smart adaptive learning and optimized feature clustering for enhanced image retrieval
title_full Smart adaptive learning and optimized feature clustering for enhanced image retrieval
title_fullStr Smart adaptive learning and optimized feature clustering for enhanced image retrieval
title_full_unstemmed Smart adaptive learning and optimized feature clustering for enhanced image retrieval
title_short Smart adaptive learning and optimized feature clustering for enhanced image retrieval
title_sort smart adaptive learning and optimized feature clustering for enhanced image retrieval
topic Content-Based image retrieval
Convolutional neural network
Elite opposition learning
Entropy-based divergence function
Golden Jackal optimization
Scaling factor
url https://doi.org/10.1038/s41598-025-10375-6
work_keys_str_mv AT pumaeswari smartadaptivelearningandoptimizedfeatureclusteringforenhancedimageretrieval
AT sujatapatil smartadaptivelearningandoptimizedfeatureclusteringforenhancedimageretrieval
AT parameshacharibidaredivakarachari smartadaptivelearningandoptimizedfeatureclusteringforenhancedimageretrieval
AT przemysławfalkowskigilski smartadaptivelearningandoptimizedfeatureclusteringforenhancedimageretrieval