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{181782,
        author = {M.DIVYA and Dr S. Sukumaran},
        title = {DEEP LEARNING FUZZY CONCEPT ANALYSIS METHOD FOR PATTERN ANALYSIS OF TEXT IN IMAGES},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {5492-5500},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181782},
        abstract = {Machine learning is a form of data analysis that employs automation to create analytical models. Machine learning, a kind of artificial intelligence, operates on the premise that robots can identify patterns in data, derive conclusions, and make decisions with minimal human intervention. The fundamental objective of pattern recognition, regardless of whether supervised or unsupervised, is classification. Among the several contexts in which pattern recognition has evolved, the statistical methodology has been the most thoroughly examined and applied in practice. Recent years have witnessed a heightened interest in neural network methodologies and strategies rooted in statistical learning theory. Key considerations in the design of a recognition system encompass the delineation of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, training and test sample selection, and performance evaluation. The overarching issue of identifying intricate patterns within random patterns of varying scale, orientation, and location persists unresolved. This research presents a text extraction pipeline designed to extract text from diverse high-quality photos sourced from social media. Following the classification of the input photographs, they are subjected to class-specific preprocessing, including text localization and illumination improvement. The structured representation developed in the prior stage facilitates the discovery of association rules, the identification of prevalent keywords, and the execution of sentiment analysis through an optical character and image recognition automatic (OCIRA) methodology that utilizes a collection of positive and negative terms. The proposed work recognizes the image related to text using deep learning method using optical character and image recognition automatic gives the best results for every tweet is assigned a score according to a scoring function.},
        keywords = {Information Retrieval, Fuzzy Concept Analysis, Pattern Retrieval, Pattern Mining, Optical character and Image Recognition automatic, Sentiment Image Analysis},
        month = {June},
        }