A Transformer-Driven Clustering Framework for Image-Based Document Segregation of OCR-Extracted Data
Preprint
- 10 September 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
The rapid increase in image-based documents across industries such as healthcare, law, and government underscores the need for efficient techniques to organize and extract meaningful insights from unstructured datasets. Traditional methods, including manual sorting and rule-based clustering, fail to effectively handle large-scale, noisy, and heterogeneous datasets, highlighting a significant research gap. To address this, we propose the Enhancing Document Segregation (EDS) model, a framework designed to cluster image-based datasets using a combination of Optical Character Recognition (OCR), semantic analysis, and advanced clustering algorithms. The EDS pipeline extracts text from images via OCR, preprocesses the data to eliminate noise, and generates embeddings using transformer-based models to capture semantic relationships. These embeddings are clustered using K-means, DBSCAN, Gaussian Mixture Models, and agglomerative clustering techniques to verify changes in variable data. Empirical analysis demonstrates the robustness of the EDS model in improving clustering accuracy and efficiency, particularly in noisy and complex datasets. Integrating theoretical foundations with practical clustering methodologies ensures the EDS model delivers a scalable solution for real-world challenges, enhancing document organization and retrieval in critical domains.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- ClusterTabNet: Supervised Clustering Method for Table Detection and Table Structure Recognition2024
- Towards Metric DBSCAN: Exact, Approximate, and Streaming AlgorithmsProceedings of the ACM on Management of Data, 2024
- Automated Multi-Page Document Classification and Information Extraction for Insurance Applications using Deep Learning Techniques2024
- TeraHAC: Hierarchical Agglomerative Clustering of Trillion-Edge GraphsProceedings of the ACM on Management of Data, 2023
- Harnessing Deep Learning Techniques for Text Clustering and Document CategorizationInternational Journal on Recent and Innovation Trends in Computing and Communication, 2023
- A Hybrid Machine Learning Approach for Document Classification: A Comparative Study2023
- Research proposal content extraction using natural language processing and semi-supervised clustering: A demonstration and comparative analysisScientometrics, 2023
- Multi-Label Classification via Adaptive Resonance Theory-Based ClusteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Sublinear Algorithms for Hierarchical Clustering2022
- Unsupervised deep clustering via adaptive GMM modeling and optimizationNeurocomputing, 2021