# Improving Document Binarization via Adversarial Noise-Texture Augmentation

arXiv: https://arxiv.org/abs/1810.11120 · HTML: https://mlsanity.com/paper/1810.11120/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2018.

## Built on by (most cited first, 9 of 9)

- [DocEnTr: An End-to-End Document Image Enhancement Transformer](https://mlsanity.com/paper/2201.10252/) (2022)
- [Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancement](https://mlsanity.com/paper/2105.12710/) (2021)
- [Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks](https://mlsanity.com/paper/2211.16098/) (2022)
- [Binarizing Documents by Leveraging both Space and Frequency](https://mlsanity.com/paper/2404.17243/) (2024)
- [CCDWT-GAN: Generative Adversarial Networks Based on Color Channel Using Discrete Wavelet Transform for Document Image Binarization](https://mlsanity.com/paper/2305.17420/) (2023)
- [A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancement](https://mlsanity.com/paper/2312.03946/) (2023)
- [LS-HDIB: A Large Scale Handwritten Document Image Binarization Dataset](https://mlsanity.com/paper/2101.11674/) (2021)
- [Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realisation](https://mlsanity.com/paper/2310.00546/) (2023)
- [Variational Augmentation for Enhancing Historical Document Image Binarization](https://mlsanity.com/paper/2211.06581/) (2022)

## Abstract (arXiv)

Binarization of degraded document images is an elementary step in most of the problems in document image analysis domain. The paper re-visits the binarization problem by introducing an adversarial learning approach. We construct a Texture Augmentation Network that transfers the texture element of a degraded reference document image to a clean binary image. In this way, the network creates multiple versions of the same textual content with various noisy textures, thus enlarging the available document binarization datasets. At last, the newly generated images are passed through a Binarization network to get back the clean version. By jointly training the two networks we can increase the adversarial robustness of our system. Also, it is noteworthy that our model can learn from unpaired data. Experimental results suggest that the proposed method achieves superior performance over widely used DIBCO datasets.