Confidence Prediction for Lexicon-Free OCR
Abstract
Having a reliable accuracy score is crucial for real world applications of OCR, since such systems are judged by the number of false readings. Lexicon-based OCR systems, which deal with what is essentially a multi-class classification problem, often employ methods explicitly taking into account the lexicon, in order to improve accuracy. However, in lexicon-free scenarios, filtering errors requires an explicit confidence calculation. In this work we show two explicit confidence measurement techniques, and show that they are able to achieve a significant reduction in misreads on both standard benchmarks and a proprietary dataset.
Cite
Text
Mor and Wolf. "Confidence Prediction for Lexicon-Free OCR." IEEE/CVF Winter Conference on Applications of Computer Vision, 2018. doi:10.1109/WACV.2018.00030Markdown
[Mor and Wolf. "Confidence Prediction for Lexicon-Free OCR." IEEE/CVF Winter Conference on Applications of Computer Vision, 2018.](https://mlanthology.org/wacv/2018/mor2018wacv-confidence/) doi:10.1109/WACV.2018.00030BibTeX
@inproceedings{mor2018wacv-confidence,
title = {{Confidence Prediction for Lexicon-Free OCR}},
author = {Mor, Noam and Wolf, Lior},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2018},
pages = {218-225},
doi = {10.1109/WACV.2018.00030},
url = {https://mlanthology.org/wacv/2018/mor2018wacv-confidence/}
}