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{194607,
        author = {Atharva Kadu and Suyash Nemade and Gaurang Deotale and Hakimmudin Idris Ali and Pranav G. Kale and Sunil R. Gupta},
        title = {Artificial Intelligence based Image Retrieval Using Natural Language},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {8074-8086},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194607},
        abstract = {Effective and significant image retrieval has become a major challenge due to the quick expansion of digital image collections from personal devices, surveillance systems, and online platforms. The semantic relationships found in visual data are frequently missed by conventional metadata-based and content-based image retrieval techniques. This survey examines AI-based semantic image retrieval systems that let users use natural language queries to search for images. In order to maintain semantic alignment between modalities, the system uses a pretrained CLIP transformer model to jointly encode textual descriptions and images into a shared embedding space. Cosine distance is used to calculate image-text similarity, and FAISS- based indexing guarantees quick and scalable nearest-neighbor search. Because the entire framework runs offline, data security and privacy are guaranteed. When compared to traditional retrieval, experimental results show enhanced semantic accuracy and contextual relevance. By successfully bridging the semantic gap between human queries and visual content, the suggested system lays the groundwork for clever and user-friendly visual search applications.},
        keywords = {Semantic Search, Multimodal Embeddings, Zero-Shot Retrieval, CLIP, FAISS, Offline Search},
        month = {March},
        }