UDBNET: Unsupervised Document Binarization Network via Adversarial Game

TL;DR

This paper introduces UDBNET, an unsupervised document binarization method using a three-player adversarial game, which generates pseudo paired data to improve binarization without requiring labeled datasets.

Contribution

The paper proposes a novel three-player adversarial framework for unsupervised document binarization, enlarging datasets and improving performance without paired training data.

Findings

Outperforms state-of-the-art on DIBCO datasets

Generates diverse degraded images for training

Enforces distribution alignment via joint discriminator

Abstract

Degraded document image binarization is one of the most challenging tasks in the domain of document image analysis. In this paper, we present a novel approach towards document image binarization by introducing three-player min-max adversarial game. We train the network in an unsupervised setup by assuming that we do not have any paired-training data. In our approach, an Adversarial Texture Augmentation Network (ATANet) first superimposes the texture of a degraded reference image over a clean image. Later, the clean image along with its generated degraded version constitute the pseudo paired-data which is used to train the Unsupervised Document Binarization Network (UDBNet). Following this approach, we have enlarged the document binarization datasets as it generates multiple images having same content feature but different textual feature. These generated noisy images are then fed into the UDBNet to get back the clean version. The joint discriminator which is the third-player of our three-player min-max adversarial game tries to couple both the ATANet and UDBNet. The three-player min-max adversarial game stops, when the distributions modelled by the ATANet and the UDBNet align to the same joint distribution over time. Thus, the joint discriminator enforces the UDBNet to perform better on real degraded image. The experimental results indicate the superior performance of the proposed model over existing state-of-the-art algorithm on widely used DIBCO datasets. The source code of the proposed system is publicly available at https://github.com/VIROBO-15/UDBNET.