Current Volume 8
In the multimedia domain, which includes image retrieval, pattern recognition, etc., content-based image retrieval, or CBIR, has expanded quickly. An efficient method for searching and retrieving images from pool image databases is offered by CBIR. Gaining knowledge about efficient relevance metrics is essential for enhancing image retrieval systems' functionality. Novel texture feature families include descriptors such as GLCM and LBP. The three main components of the Combined Multiple Texture Features Methods are (i) the extraction of significant texture features, (ii) fused features like LBP and GLCM, and (iii) the use of different distance metrics, including Euclidean, D1, Canberra, and Manhattan distance metrics, to identify similar pixel values. The research focuses on the picture re-ranking approach, which is a quick and accurate way to search for and identify related photos based upon their texture feature richness. These techniques, which combine the revising system and moderation of current image retrieval methods, are sometimes referred to as hybrid approaches with visual characteristics in low-level features. In the end, a user is satisfied when the required image is returned, demonstrating that the suggested approach is more successful than alternative approaches and proving that it finds the best and most accurate results.
CBIR, Multiple features, LBP, GLCM features, and Distance metrics.
IRE Journals:
Amjad Khan , V. Suresh Kumar
"Optimizing Image Retrieval through Fusion of GLCM and Local Binary Features" Iconic Research And Engineering Journals Volume 8 Issue 9 2025 Page 1567-1578
IEEE:
Amjad Khan , V. Suresh Kumar
"Optimizing Image Retrieval through Fusion of GLCM and Local Binary Features" Iconic Research And Engineering Journals, 8(9)