Almaarefa University
The authoritative source for research information and outputs is Elsevier Scopus, with researcher profile verification from the Deanship of Scientific Research.
ArticleClosed20243 citation

Content-based image retrieval by classification with reinforcement optimisation evolutionary machine learning with applications

Anandh Sam Chandra Bose ✉،Laxman Singh،Shamimul Qamar،S. Uma،L. Sherly Puspha Annabel،Sanjay Singla

Journal of Experimental & Theoretical Artificial Intelligence · vol. 37 (7) · 1195-1215 · 2024

Abstract

Content Based Image Retrieval (CBIR) plays a significant role in identifying the similarity of images with large datasets. It is identified based on the size, colour, and texture features of the image. But in such conditions, it is complex to determine the features of query images in large datasets and does not show accurate similarity when compared with every image in the retrieval process. In order to perform an efficient similarity of images, a novel Machine Learning (ML) approach Kernelized Radial Basis Auto-Encoder Function Neural Network (Ker_RadBAEFNN) technique is proposed that performs the individual image classification in the retrieval process. Moreover, the neural networks are optimised based on the reinforcement process and perform the extraction process regarding individual images. Further,reinforcement-based optimisation estimates the images in neural networks for undertaking an automatic feature extraction of query images. The performance of the classification process is validated based on MNIST, METU, and COCO datasets that determined the efficiency of the recognition and classification process of image retrieval. The experimental analysis is carried out based on various measures such as accuracy, precision, recall, F1-score, RMSE, and MAPE for the proposed and existing GLCM-ABC, PSO-ANN, IRB-CNN, FAGWO, and OCAM methods. The analysis shows that the performance of the proposed attained better effectiveness with attained accuracy by 98% and diminished for state-of-the-art techniques as 92%, 95%, 94%, 96.8%, as well as 96%, respectively. Compared to existing methods, the accuracy rate of the proposed method is maximised by 1.3%.

Details

Journal
Journal of Experimental & Theoretical Artificial Intelligence
Publisher
Taylor & Francis
Volume
37
Issue
7
Pages
1195-1215
ISSN
0952-813X
Year
2024
Language
en
License
—
Open access
Closed
Citations
3
Source
scopus

Topics

Reinforcement learningComputer scienceArtificial intelligenceContent-based image retrievalMachine learningImage retrieval

Image Retrieval and Classification Techniques (Computer Science) · Advanced Image and Video Retrieval Techniques (Computer Science) · Information Retrieval and Search Behavior (Computer Science)

Cite this

APA
Bose, A. S. C., Singh, L., Qamar, S., Uma, S., Annabel, L. S. P., Singla, S. (2024). Content-based image retrieval by classification with reinforcement optimisation evolutionary machine learning with applications. Journal of Experimental & Theoretical Artificial Intelligence, 37(7), 1195-1215. https://doi.org/10.1080/0952813x.2024.2383652
Harvard
Bose, A. S. C., Singh, L., Qamar, S., Uma, S., Annabel, L. S. P., Singla, S. 2024, 'Content-based image retrieval by classification with reinforcement optimisation evolutionary machine learning with applications', Journal of Experimental & Theoretical Artificial Intelligence, vol. 37(7), 1195-1215. Available at: https://doi.org/10.1080/0952813x.2024.2383652
Vancouver
Bose ASC, Singh L, Qamar S, Uma S, Annabel LSP, Singla S. Content-based image retrieval by classification with reinforcement optimisation evolutionary machine learning with applications. Journal of Experimental & Theoretical Artificial Intelligence. 2024;37(7), 1195-1215.
BibTeX
@article{bose20241226,
  title = {Content-based image retrieval by classification with reinforcement optimisation evolutionary machine learning with applications},
  author = {Anandh Sam Chandra Bose and Laxman Singh and Shamimul Qamar and S. Uma and L. Sherly Puspha Annabel and Sanjay Singla},
  year = {2024},
  journal = {Journal of Experimental & Theoretical Artificial Intelligence},
  volume = {37},
  number = {7},
  pages = {1195-1215},
  publisher = {Taylor & Francis},
  doi = {10.1080/0952813x.2024.2383652},
  url = {https://doi.org/10.1080/0952813x.2024.2383652}
}
RIS
TY  - JOUR
AU  - Anandh Sam Chandra Bose
AU  - Laxman Singh
AU  - Shamimul Qamar
AU  - S. Uma
AU  - L. Sherly Puspha Annabel
AU  - Sanjay Singla
TI  - Content-based image retrieval by classification with reinforcement optimisation evolutionary machine learning with applications
PY  - 2024
JO  - Journal of Experimental & Theoretical Artificial Intelligence
VL  - 37
IS  - 7
SP  - 1195-1215
DO  - 10.1080/0952813x.2024.2383652
UR  - https://doi.org/10.1080/0952813x.2024.2383652
ER  -