Improving Document Binarization via Adversarial Noise-Texture Augmentation

TL;DR

This paper introduces an adversarial learning framework with a Texture Augmentation Network to generate diverse noisy document images, enhancing binarization robustness and performance on degraded document datasets.

Contribution

It presents a novel adversarial approach that creates augmented training data with varied textures, improving document binarization accuracy and robustness, even from unpaired data.

Findings

Outperforms existing methods on DIBCO datasets

Generates diverse noisy textures for training augmentation

Enhances robustness of binarization models

Abstract

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.