Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
This paper presents a Content-Based Image Retrieval (CBIR) system that utilizes a Vector Space Model (VSM) combined with advanced Natural Language Processing (NLP) techniques and user relevance feedback to improve image search accuracy and efficiency. The proposed framework incorporates NLP to parse user queries, generate synonyms, and construct SQL queries for feature extraction. It leverages a novel quadtree-based feature extraction method using a Vision Transformer to capture fine-grained image details. Crucially, the system incorporates both binary (like/dislike) and textual feedback from users to dynamically adjust feature weights and incorporate new, user-provided keywords. By assigning weights to relevant features derived from the Vision Transformer's probabilistic outputs and user feedback, the system enhances the retrieval process, enabling more precise and personalized matching of images.
Keywords:
Content-Based Image Retrieval (CBIR), Vector Space Model (VSM), Natural Language Processing (NLP), SQL Query Generation, Feature Extraction, Synonym Expansion, Machine Learning, Image Classification, Image Features, Data Processing, Search Algorithms, User Interaction, User Relevance Feedback, Binary Feedback, Textual Feedback, Adaptive Retrieval, Relevance Ranking, Corel 1k Dataset
Cite Article:
"Content-Based Image Retrieval System Utilizing Vision Transformer", International Journal of Science & Engineering Development Research (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 2, page no.a786-a790, February-2025, Available :http://www.ijrti.org/papers/IJRTI2502080.pdf
Downloads:
00099
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator