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{174057,
        author = {NAYAKULA UPENDER and D. CELESTY BLISS RUFUS and JAGADEESH GONELA and Y. MALLIKARJUN},
        title = {Optimized Fusion of Shape and Texture Features for Medical Image Retrieval},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {4802-4809},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174057},
        abstract = {In the realm of image retrieval, the fusion of shape and texture features has emerged as a promising approach to improve accuracy and efficiency. This study presents a novel method that employs Convolutional Neural Networks (CNNs) for extracting texture features, specifically utilizing the VGG16 pre-trained model, renowned for its deep learning capabilities in image classification. Concurrently, Complex Zernike Moments are employed to capture the shape characteristics of images. To quantify the similarity between the retrieved images, cosine similarity is utilized as the metric of choice. The integration of these two distinct feature sets aims to optimize image retrieval performance, providing a comprehensive framework that leverages both texture and shape information. Experimental results demonstrate significant improvements in retrieval accuracy compared to traditional methods, highlighting the effectiveness of this feature fusion approach.},
        keywords = {Image Retrieval, Feature Fusion, Shape Features, Texture Features, Convolutional Neural Networks (CNN), VGG16, Complex Zernike Moments, Cosine Similarity, Deep Learning, Computer Vision.},
        month = {April},
        }