Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191577,
        author = {shiva},
        title = {A Hybrid Content-Based Image Retrieval System for Super-Resolution Images Using Deep and Hand-Crafted Feature Fusion},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {7104-7108},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191577},
        abstract = {Content-Based Image Retrieval (CBIR) has emerged as a crucial technique for efficiently retrieving relevant images from large-scale visual databases. However, existing CBIR systems often rely solely on either deep learning-based features or traditional hand-crafted descriptors, resulting in limited retrieval accuracy due to the semantic gap between low-level visual features and high-level human perception. This paper proposes an enhanced hybrid CBIR framework specifically designed for super-resolution images by integrating deep semantic features extracted using InceptionV3 (GoogLeNet) with complementary hand-crafted features, namely Modified Dot Diffusion Block Truncation Coding (DDBTC), Histogram of Oriented Gradients (HOG), and Gray-Level Co-occurrence Matrix (GLCM). To improve feature quality, images from the VISTEX and STEX datasets are first enhanced using INTER-CUBIC interpolation for super-resolution. The extracted deep and hand-crafted features are fused into a unified representation, and similarity matching is performed using Euclidean distance. Experimental results demonstrate that the proposed hybrid approach significantly improves precision, recall, and F-measure when compared to standalone deep learning-based CBIR models, highlighting its effectiveness for high-resolution image retrieval applications.},
        keywords = {Content-Based Image Retrieval, Super-Resolution, Deep Learning, GoogLeNet, Feature Fusion, Texture Analysis.},
        month = {January},
        }