| Volume 2 Issue 1 (2026) | Published in 2026-01-25
An Efficient Content-Based Image Retrieval System for Clothing Images Using Color–Texture Fusion and K-means Clustering
-
ABSTRACT
The rapid growth of digital images, particularly in e-commerce platforms, has increased the need for efficient image retrieval systems. Traditional text-based retrieval methods suffer from limitations such as subjectivity and high annotation cost. Therefore, Content-Based Image Retrieval (CBIR) systems have been developed to utilize visual features such as color and texture.
This research proposes a CBIR system for clothing images that combines color and texture features with K-means clustering to improve both accuracy and efficiency. Color features are extracted using HSV histograms, while texture features are derived from the Gray Level Co-occurrence Matrix (GLCM). The features are fused using equal weighting, and similarity is computed using Euclidean distance.
Recent studies emphasize the importance of combining multiple features and efficient indexing techniques to improve retrieval performance]. Experimental results show that the proposed system achieves improved precision while significantly reducing retrieval time through clustering.
Keywords: Content-Based Image Retrieval (CBIR); Clothing Image Retrieval; Color–Texture Fusion; K-means Clustering; HSV Color Histogram; Gray Level Co-occurrence Matrix (GLCM).
-
test
-
المراجع
References
1. Z. Hu and A. G. Bors, “Co-attention enabled content-based image retrieval,” Neural Networks, vol. 164, pp. 245–263, 2023.
2. Abbas, T. N. A., Hameed, R., Kadhim, A. A., & Qasim, N. H. (2024). Artificial intelligence and criminal liability: Exploring the legal implications of AI-enabled crimes. Encuentros: Revista de Ciencias Humanas, Teoría Social y Pensamiento Crítico, (22), 140–159. https://doi.org/10.5281/zenodo.13386675
3. Alsmadi, M. S., Kadhim, A. A., Balas, H. A., & Al-Sarhan, M. (2025). Amendments to cloud computing contracts. Journal of Human Security, 21(2), 59–66. https://doi.org/10.12924/johs2025.210209
4. H. Qazanfari, M. M. AlyanNezhadi, and Z. N. Khoshdaregi, “Advancements in content-based image retrieval: A survey of relevance feedback techniques,” arXiv preprint arXiv:2312.10089, 2023.
5. A. Orman, “Content-based image retrieval using composite feature vectors with color and pixel similarity,” Turkish Journal of Engineering, 2024.
6. L. Pinjarkar, P. K. Sharma, and R. Gupta, “Deep learning model for retrieving color logo images in CBIR,” Journal of Electrical Systems, vol. 20, no. 2, 2024.
7. A. Rouhafzay, N. Baaziz, and M. S. Allili, “Texture image retrieval using classification and contourlet-based features,” arXiv preprint arXiv:2403.06048, 2024.
8. G. Gopu and D. Dunna, “Advances in unsupervised learning for image retrieval systems,” 2024.
9. Y. Wang, X. Li, and H. Zhang, “Feature fusion for fabric image retrieval using color and texture analysis,” 2024.
10. J. John, S. Thomas, and A. Paul, “Siamese neural networks for content-based image retrieval systems,” 2024.
11. H. Wan, Y. Liu, and X. Chen, “Attribute-guided similarity learning for fashion image retrieval,” 2023.
12. M. H. Hadid, S. A. Mahmood, and R. K. Ali, “An overview of content-based image retrieval methods and techniques,” Iraqi Journal for Computer Science and Mathematics, 2023.
13. M. J. Swain and D. H. Ballard, “Color indexing,” International Journal of Computer Vision, 1991.
14. R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image classification,” IEEE Transactions on Systems, Man, and Cybernetics, 1973.
15. A. W. M. Smeulders et al., “Content-based image retrieval at the end of the early years,” IEEE TPAMI, 2000.
16. E. Yildizer, A. E. Kadiyala, et al., “A cluster-based approach for efficient image retrieval using K-means,” IEEE International Conference on Information Reuse and Integration, 2012. -
Article history_ar
Received : Nov 02, 2025
Revised : Nov 04, 2025
Accepted : Jan 20, 2026
-
Authors Affiliations_ar
Furqan Tahseen Husieen 1,*
(1) Asst. Lect, Albayan University, Baghdad International Airport Road, near Abbas Ibn Firnas Square, Iraq, Baghdad . Email: furqan.t@albayan.edu.iq
* Corresponding Author: Furqan Tahseen Husieen, furqan.t@albayan.edu.iq
-
Ethics declarations_ar
Acknowledgment None Author Contribution All authors contributed equally to the main contributor to this paper. All authors read and approved the final paper. Conflicts of Interest “The authors declare no conflict of interest.” Funding “This research received no external funding” Ethical Considerations List of Abbrevation Declaration of generative AI and AI-assisted technologies in the writing process -
Plagiarism Check_ar
Plagiarism Check AI Content Detection Notes
How to cite
Husieen, F. T. (2026). An efficient content-based image retrieval system for clothing images using color–texture fusion and K-means clustering. The International Journal of Engineering Sciences, 2(1), 1–13.
License
1