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

TL;DR

This paper introduces a novel method for document image binarization directly in the JPEG compressed domain using Dual Discriminator GANs, achieving state-of-the-art results without full image decompression.

Contribution

The paper proposes a dual discriminator GAN framework that binarizes JPEG compressed images directly, reducing computational costs and improving robustness over existing pixel-based methods.

Findings

Achieved state-of-the-art performance on DIBCO datasets.

Demonstrated robustness to noisy and degraded document images.

Reduced processing time and memory usage compared to traditional methods.

Abstract

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.