# Document Image Binarization in JPEG Compressed Domain using Dual Discriminator Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2209.05921 · HTML: https://mlsanity.com/paper/2209.05921/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 13 Sep 2022.

## Builds on (most cited first, 10 of 10)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Residual Learning in the JPEG Transform Domain](https://mlsanity.com/paper/1812.11690/) (2018)
- [DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement](https://mlsanity.com/paper/2010.08764/) (2020)
- [Document Image Binarization with Fully Convolutional Neural Networks](https://mlsanity.com/paper/1708.03276/) (2017)
- [DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients](https://mlsanity.com/paper/1907.11503/) (2019)
- [Persian Heritage Image Binarization Competition (PHIBC 2012)](https://mlsanity.com/paper/1306.6263/) (2013)
- [Two-stage generative adversarial networks for document image binarization with color noise and background removal](https://mlsanity.com/paper/2010.10103/) (2020)
- [Learning to Clean: A GAN Perspective](https://mlsanity.com/paper/1901.11382/) (2019)
- [UDBNET: Unsupervised Document Binarization Network via Adversarial Game](https://mlsanity.com/paper/2007.07075/) (2020)
- [Degraded Historical Documents Images Binarization Using a Combination of Enhanced Techniques](https://mlsanity.com/paper/1901.09425/) (2019)

## Abstract (arXiv)

Image binarization techniques are being popularly used in enhancement of noisy and/or degraded images catering different Document Image Anlaysis (DIA) applications like word spotting, document retrieval, and OCR. Most of the existing techniques focus on feeding pixel images into the Convolution Neural Networks to accomplish document binarization, which may not produce effective results when working with compressed images that need to be processed without full decompression. Therefore in this research paper, the idea of document image binarization directly using JPEG compressed stream of document images is proposed by employing Dual Discriminator Generative Adversarial Networks (DD-GANs). Here the two discriminator networks - Global and Local work on different image ratios and use focal loss as generator loss. The proposed model has been thoroughly tested with different versions of DIBCO dataset having challenges like holes, erased or smudged ink, dust, and misplaced fibres. The model proved to be highly robust, efficient both in terms of time and space complexities, and also resulted in state-of-the-art performance in JPEG compressed domain.