• Mrs. JALA SRAVANTHI
• Ms. MADOORI HARITHA
• Mr. SINGAM SAI KIRAN
• Ms. NAGILLA SUDEEPTHI
• Ms. ARPULA GAYATHRI

With the rising popularity of image-sharing platforms such as Flickr, there is a growing focus among scholars on tag-based image retrieval (TBIR). TBIR serves as a crucial method for locating images contributed by social users. While previous research in this domain has explored tag information and various visual features, many existing methods tend to use these visual features in isolation or in a sequential manner. This paper introduces a novel approach for the fusion of global and local visual features to discern the relevance of images through a hypergraph approach. Initially, a hypergraph is constructed by leveraging global and local visual features along with tag information. Subsequently, we propose a pseudo-relevance feedback mechanism to identify pseudo-positive images. Finally, employing the hypergraph and pseudo-relevance feedback, we apply a hypergraph learning algorithm to compute the relevance score for each image concerning the query. The experimental results underscore the efficacy of the proposed approach, demonstrating its ability to enhance image retrieval in tag-based systems.

JOINT HYPERGRAPH LEARNING FOR TAG-BASED IMAGE RETRIEVAL

"JOINT HYPERGRAPH LEARNING FOR TAG-BASED IMAGE RETRIEVAL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.f228-f237, March-2024, Available :http://www.jetir.org/papers/JETIR2403526.pdf

"JOINT HYPERGRAPH LEARNING FOR TAG-BASED IMAGE RETRIEVAL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppf228-f237, March-2024, Available at : http://www.jetir.org/papers/JETIR2403526.pdf