Keyword Extraction From Manuscript Images: Scholarly Access and Sustainable Preservation of India’s Classical Knowledge Systems
Author(s): Shiva Kanaujia Sukula
Abstract - One of the major research concerns have grown in the area of keyword extraction from manuscript images during last decade. Manuscripts, specially found in Sanskrit language have observed the keyword extraction from images and this has developed a lot curiosity among the professionals and scholars. The emergence of technological innovations as well as including them for the implementation purposes have advanced the functionality as well as research attention. These innovations are comprised of computer vision, language processing under the umbrella of artificial intelligence. The literature has shown inclination towards recognition accuracy and deep-learning; the examples include OCR systems as well as CNN-BiLSTM in the Sanskrit manuscript. The complexity of Sanskrit manuscripts and images in them reflect need of increasingly efficient techniques. The requirement of advanced preprocessing, segmentation methods, and other steps in order to improve the quality of manuscripts for further information retrieval and access are much paid attention….
Keywords - Sanskrit manuscripts, OCR, keyword extraction, images, deep learning, NLP, digitization, heritage preservation, Devanāgarī
DOI URL: https://doi.org/10.26761/ijrls.11.4.2025.1977
Cite This Article As:, Sukula, S.K. (2025) Keyword Extraction From Manuscript Images: Scholarly Access and Sustainable Preservation of India’s Classical Knowledge Systems. International Journal of Research in Library Science (IJRLS), 11(4) 79-99. www.ijrls.in
Copyright © 2025 Author(s) retains the copyright of this article. This article is published under the terms of the Creative Commons Attribution License 4.0.
Paper ID: IJRLS-1977 Page: 79-99 Publication Date: 30 October 2025