Low-Resource Heuristics for Bahnaric Optical Character Recognition Improvement

TL;DR

This paper presents a novel OCR enhancement framework for the Bahnar language, combining detection algorithms and probabilistic heuristics to improve digitization accuracy of degraded documents, aiding language preservation efforts.

Contribution

It introduces a comprehensive approach integrating detection techniques with error correction heuristics specifically for Bahnar OCR, addressing data scarcity and degradation challenges.

Findings

Recognition accuracy improved from 72.86% to 79.26%

Effective for degraded and limited-resource language documents

Provides a framework applicable to other minority languages

Abstract

Bahnar, a minority language spoken across Vietnam, Cambodia, and Laos, faces significant preservation challenges due to limited research and data availability. This study addresses the critical need for accurate digitization of Bahnar language documents through optical character recognition (OCR) technology. Digitizing scanned paper documents poses significant challenges, as degraded image quality from broken or blurred areas introduces considerable OCR errors that compromise information retrieval systems. We propose a comprehensive approach combining advanced table and non-table detection techniques with probability-based post-processing heuristics to enhance recognition accuracy. Our method first applies detection algorithms to improve input data quality, then employs probabilistic error correction on OCR output. Experimental results indicate a substantial improvement, with recognition accuracy increasing from 72.86% to 79.26%. This work contributes valuable resources for Bahnar language preservation and provides a framework applicable to other minority language digitization efforts.