# A selectional auto-encoder approach for document image binarization

arXiv: https://arxiv.org/abs/1706.10241 · HTML: https://mlsanity.com/paper/1706.10241/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2017.

## Built on by (most cited first, 22 of 22)

- [DocEnTr: An End-to-End Document Image Enhancement Transformer](https://mlsanity.com/paper/2201.10252/) (2022)
- [Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement](https://mlsanity.com/paper/2203.04814/) (2022)
- [SauvolaNet: Learning Adaptive Sauvola Network for Degraded Document Binarization](https://mlsanity.com/paper/2105.05521/) (2021)
- [Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancement](https://mlsanity.com/paper/2105.12710/) (2021)
- [A Survey on Deep learning based Document Image Enhancement](https://mlsanity.com/paper/2112.02719/) (2021)
- [Mixed Model OCR Training on Historical Latin Script for Out-of-the-Box Recognition and Finetuning](https://mlsanity.com/paper/2106.07881/) (2021)
- [Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks](https://mlsanity.com/paper/2211.16098/) (2022)
- [DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarization](https://mlsanity.com/paper/2312.03568/) (2023)
- [DocStormer: Revitalizing Multi-Degraded Colored Document Images to Pristine PDF](https://mlsanity.com/paper/2310.17910/) (2023)
- [Neuromorphic Synergy for Video Binarization](https://mlsanity.com/paper/2402.12644/) (2024)
- [Efficient Generative Adversarial Networks for Color Document Image Enhancement and Binarization Using Multi-scale Feature Extraction](https://mlsanity.com/paper/2407.04231/) (2024)
- [MFE-GAN: Efficient GAN-based Framework for Document Image Enhancement and Binarization with Multi-scale Feature Extraction](https://mlsanity.com/paper/2512.14114/) (2025)
- [Paired Image to Image Translation for Strikethrough Removal From Handwritten Words](https://mlsanity.com/paper/2201.09633/) (2022)
- [DECDM: Document Enhancement using Cycle-Consistent Diffusion Models](https://mlsanity.com/paper/2311.09625/) (2023)
- [A Fair Evaluation of Various Deep Learning-Based Document Image Binarization Approaches](https://mlsanity.com/paper/2401.11831/) (2024)
- [LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approach](https://mlsanity.com/paper/2406.08610/) (2024)
- [Analysis of PDE-based binarization model for degraded document images](https://mlsanity.com/paper/2111.05471/) (2021)
- [Variational Augmentation for Enhancing Historical Document Image Binarization](https://mlsanity.com/paper/2211.06581/) (2022)
- [Proceedings of the 3rd International Workshop on Reading Music Systems](https://mlsanity.com/paper/2212.00378/) (2022)
- [Partial differential equation system for binarization of degraded document images](https://mlsanity.com/paper/2503.08017/) (2025)
- [See Silhouettes in Motion with Neuromorphic Vision](https://mlsanity.com/paper/2605.17984/) (2026)
- [ENet-GP: Unified Document Image Restoration](https://mlsanity.com/paper/2609.33758/) (2026)

## Abstract (arXiv)

Binarization plays a key role in the automatic information retrieval from document images. This process is usually performed in the first stages of documents analysis systems, and serves as a basis for subsequent steps. Hence it has to be robust in order to allow the full analysis workflow to be successful. Several methods for document image binarization have been proposed so far, most of which are based on hand-crafted image processing strategies. Recently, Convolutional Neural Networks have shown an amazing performance in many disparate duties related to computer vision. In this paper we discuss the use of convolutional auto-encoders devoted to learning an end-to-end map from an input image to its selectional output, in which activations indicate the likelihood of pixels to be either foreground or background. Once trained, documents can therefore be binarized by parsing them through the model and applying a threshold. This approach has proven to outperform existing binarization strategies in a number of document domains.