Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)

<Previous Article In Volume
Next Article In Volume>

An Explainable CNN-Based Deep Learning Framework for Content-Based Image Retrieval

Authors
P. B. Nagaraju1, *, Gaddikoppula Anil Kumar2, Amjan Shaik3
1Department of CSE Bhartiya Engineering Science and Technology Innovation University (BESTIU), AP & IT Department, S.R. K.R. Engineering College(A), Bhimavaram, Andhra Pradesh, India
2Department of CSE, Scient Institute of Technology, Ibrahimpatnam, P.R. District, Telangana, India
3Department of CSE, St. Peter’s Engineering College, Maisammaguda, Hyderabad, Telangana, India
*Corresponding author. Email: nagup84@gmail.com
Corresponding Author
P. B. Nagaraju
Available Online 31 December 2025.
DOI
10.2991/978-94-6463-978-0_16How to use a DOI?
Keywords
Content-Based Image Retrieval; Deep Learning; Explainable AI; ResNet50; Grad-CAM
Abstract

The use of deep learning-based CBIR models, particularly those incorporating convolutional nets (CNNs), meanwhile addressed some problems by learning hierarchical features automatically. However, most models now available fail to be interpretable and transparent. This limits their application in sensitive areas. In order to meet these challenges, we introduce Explain CBIR-Net, a novel and insightful deep learning model that not only improves the accuracy of CBIR but also makes it easy to understand. By use of a ResNet50-based CNN framework, we optimize for powerful feature extraction and hence quick massively directed retrieval. In addition, we integrate the Grad-CAMexplain module with focus on our retrieval, so that the entire process is open and reliable to users. The proposed algorithm delivers high retrieval precision while retaining interpretability. Extensive testing on the Mini-ImageNet datasets reveals that our ExplainCBIR-Net framework outperforms existing image retrieval methods. The framework offers a mean average precision (mAP) of 97.23 %, significantly boosting the accuracy of recall and F1-score indicators for baseline models such as VGG16 and ResNet18.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
Series
Advances in Engineering Research
Publication Date
31 December 2025
ISBN
978-94-6463-978-0
ISSN
2352-5401
DOI
10.2991/978-94-6463-978-0_16How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - P. B. Nagaraju
AU  - Gaddikoppula Anil Kumar
AU  - Amjan Shaik
PY  - 2025
DA  - 2025/12/31
TI  - An Explainable CNN-Based Deep Learning Framework for Content-Based Image Retrieval
BT  - Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
PB  - Atlantis Press
SP  - 172
EP  - 188
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-978-0_16
DO  - 10.2991/978-94-6463-978-0_16
ID  - Nagaraju2025
ER  -