# Binarizing Documents by Leveraging both Space and Frequency

arXiv: https://arxiv.org/abs/2404.17243 · HTML: https://mlsanity.com/paper/2404.17243/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 79 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Builds on (most cited first, 22 of 22)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [A General and Adaptive Robust Loss Function](https://mlsanity.com/paper/1701.03077/) (2017)
- [Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks](https://mlsanity.com/paper/1710.01992/) (2017)
- [DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement](https://mlsanity.com/paper/2010.08764/) (2020)
- [DocDiff: Document Enhancement via Residual Diffusion Models](https://mlsanity.com/paper/2305.03892/) (2023)
- [DocEnTr: An End-to-End Document Image Enhancement Transformer](https://mlsanity.com/paper/2201.10252/) (2022)
- [Document Image Binarization with Fully Convolutional Neural Networks](https://mlsanity.com/paper/1708.03276/) (2017)
- [Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution](https://mlsanity.com/paper/1809.04508/) (2018)
- [A Generalization of Otsu's Method and Minimum Error Thresholding](https://mlsanity.com/paper/2007.07350/) (2020)
- [How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning](https://mlsanity.com/paper/2305.02593/) (2023)
- [Persian Heritage Image Binarization Competition (PHIBC 2012)](https://mlsanity.com/paper/1306.6263/) (2013)
- [Improving Document Binarization via Adversarial Noise-Texture Augmentation](https://mlsanity.com/paper/1810.11120/) (2018)
- [GDB: Gated convolutions-based Document Binarization](https://mlsanity.com/paper/2302.02073/) (2023)
- [Two-stage generative adversarial networks for document image binarization with color noise and background removal](https://mlsanity.com/paper/2010.10103/) (2020)
- [Evaluating Synthetic Pre-Training for Handwriting Processing Tasks](https://mlsanity.com/paper/2304.01842/) (2023)
- [Light-weight Document Image Cleanup using Perceptual Loss](https://mlsanity.com/paper/2105.09076/) (2021)
- [Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks](https://mlsanity.com/paper/2211.16098/) (2022)
- [A Few Shot Multi-Representation Approach for N-gram Spotting in Historical Manuscripts](https://mlsanity.com/paper/2209.10441/) (2022)
- [Volumetric Fast Fourier Convolution for Detecting Ink on the Carbonized Herculaneum Papyri](https://mlsanity.com/paper/2308.05070/) (2023)
- [Unsupervised ensemble of experts (EoE) framework for automatic binarization of document images](https://mlsanity.com/paper/1305.2949/) (2013)

## Built on by (most cited first, 3 of 3)

- [Autoregressive Styled Text Image Generation, but Make it Reliable](https://mlsanity.com/paper/2510.23240/) (2025)
- [Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?](https://mlsanity.com/paper/2508.09936/) (2025)
- [A Text Recognition Dataset from Sahidic Coptic Ancient Manuscripts](https://mlsanity.com/paper/2606.15987/) (2026)

## Abstract (arXiv)

Document Image Binarization is a well-known problem in Document Analysis and Computer Vision, although it is far from being solved. One of the main challenges of this task is that documents generally exhibit degradations and acquisition artifacts that can greatly vary throughout the page. Nonetheless, even when dealing with a local patch of the document, taking into account the overall appearance of a wide portion of the page can ease the prediction by enriching it with semantic information on the ink and background conditions. In this respect, approaches able to model both local and global information have been proven suitable for this task. In particular, recent applications of Vision Transformer (ViT)-based models, able to model short and long-range dependencies via the attention mechanism, have demonstrated their superiority over standard Convolution-based models, which instead struggle to model global dependencies. In this work, we propose an alternative solution based on the recently introduced Fast Fourier Convolutions, which overcomes the limitation of standard convolutions in modeling global information while requiring fewer parameters than ViTs. We validate the effectiveness of our approach via extensive experimental analysis considering different types of degradations.