# Detection Masking for Improved OCR on Noisy Documents

arXiv: https://arxiv.org/abs/2205.08257 · HTML: https://mlsanity.com/paper/2205.08257/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 47 references that are in the map.
- First posted on arXiv 17 May 2022.

## Builds on (most cited first, 24 of 24)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation](https://mlsanity.com/paper/1809.10486/) (2018)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [EAST: An Efficient and Accurate Scene Text Detector](https://mlsanity.com/paper/1704.03155/) (2017)
- [COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images](https://mlsanity.com/paper/1601.07140/) (2016)
- [MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation](https://mlsanity.com/paper/1902.04049/) (2019)
- [Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition](https://mlsanity.com/paper/1710.10400/) (2017)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network](https://mlsanity.com/paper/1908.05900/) (2019)
- [Domain-adversarial neural networks to address the appearance variability of histopathology images](https://mlsanity.com/paper/1707.06183/) (2017)
- [A Survey of Deep Learning Approaches for OCR and Document Understanding](https://mlsanity.com/paper/2011.13534/) (2020)
- [Kleister: A novel task for Information Extraction involving Long Documents with Complex Layout](https://mlsanity.com/paper/2003.02356/) (2020)
- [MIDV-2019: Challenges of the modern mobile-based document OCR](https://mlsanity.com/paper/1910.04009/) (2019)
- [Attention-based Extraction of Structured Information from Street View Imagery](https://mlsanity.com/paper/1704.03549/) (2017)
- [Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin](https://mlsanity.com/paper/1809.05501/) (2018)
- [Text Detection and Recognition in the Wild: A Review](https://mlsanity.com/paper/2006.04305/) (2020)
- [Brno Mobile OCR Dataset](https://mlsanity.com/paper/1907.01307/) (2019)
- [DDI-100: Dataset for Text Detection and Recognition](https://mlsanity.com/paper/1912.11658/) (2019)
- [A Cost Efficient Approach to Correct OCR Errors in Large Document Collections](https://mlsanity.com/paper/1905.11739/) (2019)
- [Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition](https://mlsanity.com/paper/2009.10874/) (2020)

## Built on by (most cited first, 5 of 5)

- [Augraphy: A Data Augmentation Library for Document Images](https://mlsanity.com/paper/2208.14558/) (2022)
- [Confidence-Aware Document OCR Error Detection](https://mlsanity.com/paper/2409.04117/) (2024)
- [BusiNet -- a Light and Fast Text Detection Network for Business Documents](https://mlsanity.com/paper/2207.01220/) (2022)
- [Studying Illustrations in Manuscripts: An Efficient Deep-Learning Approach](https://mlsanity.com/paper/2601.05269/) (2025)
- [ShabbyPages: A Reproducible Document Denoising and Binarization Dataset](https://mlsanity.com/paper/2303.09339/) (2023)

## Abstract (arXiv)

Optical Character Recognition (OCR), the task of extracting textual information from scanned documents is a vital and broadly used technology for digitizing and indexing physical documents. Existing technologies perform well for clean documents, but when the document is visually degraded, or when there are non-textual elements, OCR quality can be greatly impacted, specifically due to erroneous detections. In this paper we present an improved detection network with a masking system to improve the quality of OCR performed on documents. By filtering non-textual elements from the image we can utilize document-level OCR to incorporate contextual information to improve OCR results. We perform a unified evaluation on a publicly available dataset demonstrating the usefulness and broad applicability of our method. Additionally, we present and make publicly available our synthetic dataset with a unique hard-negative component specifically tuned to improve detection results, and evaluate the benefits that can be gained from its usage