Confidence-Aware Document OCR Error Detection

TL;DR

This paper investigates how OCR confidence scores can improve error detection in OCR outputs, introduces ConfBERT which incorporates these scores, and demonstrates enhanced detection performance, highlighting disparities between OCR systems.

Contribution

The paper presents ConfBERT, a novel BERT-based model that integrates OCR confidence scores into token embeddings for improved error detection.

Findings

Integrating OCR confidence scores improves error detection accuracy.

ConfBERT outperforms baseline models in error detection tasks.

Significant performance gaps exist between commercial and open-source OCR systems.

Abstract

Optical Character Recognition (OCR) continues to face accuracy challenges that impact subsequent applications. To address these errors, we explore the utility of OCR confidence scores for enhancing post-OCR error detection. Our study involves analyzing the correlation between confidence scores and error rates across different OCR systems. We develop ConfBERT, a BERT-based model that incorporates OCR confidence scores into token embeddings and offers an optional pre-training phase for noise adjustment. Our experimental results demonstrate that integrating OCR confidence scores can enhance error detection capabilities. This work underscores the importance of OCR confidence scores in improving detection accuracy and reveals substantial disparities in performance between commercial and open-source OCR technologies.