Confidence-Aware Document OCR Error Detection
This work addresses OCR error detection for applications relying on text recognition, but it is incremental as it builds on existing BERT-based methods by incorporating confidence scores.
The paper tackled the problem of OCR accuracy challenges by exploring the use of OCR confidence scores to enhance error detection, resulting in improved detection capabilities with notable performance disparities between commercial and open-source OCR systems.
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.