Automatic Document Image Binarization using Bayesian Optimization

TL;DR

This paper introduces an automatic document image binarization method that combines a two band-pass filtering approach with Bayesian optimization to adaptively select optimal parameters, improving segmentation quality on degraded documents.

Contribution

It proposes a novel combination of filtering and Bayesian optimization for automatic hyperparameter tuning in document binarization, enhancing robustness and accuracy.

Findings

Effective on DIBCO and H-DIBCO datasets

Outperforms some existing binarization methods

Automatically adapts to various degradation levels

Abstract

Document image binarization is often a challenging task due to various forms of degradation. Although there exist several binarization techniques in literature, the binarized image is typically sensitive to control parameter settings of the employed technique. This paper presents an automatic document image binarization algorithm to segment the text from heavily degraded document images. The proposed technique uses a two band-pass filtering approach for background noise removal, and Bayesian optimization for automatic hyperparameter selection for optimal results. The effectiveness of the proposed binarization technique is empirically demonstrated on the Document Image Binarization Competition (DIBCO) and the Handwritten Document Image Binarization Competition (H-DIBCO) datasets.