A Multiple-Expert Binarization Framework for Multispectral Images

TL;DR

This paper introduces a novel multispectral image binarization framework that combines subspace selection, preprocessing, and ensemble methods to improve textual information extraction, validated on a multispectral dataset.

Contribution

It presents a new ensemble-based binarization framework utilizing subspace selection and optimization for multispectral images, enhancing performance over existing methods.

Findings

Promising results on a multispectral dataset

Effective generalization to unseen data

Improved textual information extraction

Abstract

In this work, a multiple-expert binarization framework for multispectral images is proposed. The framework is based on a constrained subspace selection limited to the spectral bands combined with state-of-the-art gray-level binarization methods. The framework uses a binarization wrapper to enhance the performance of the gray-level binarization. Nonlinear preprocessing of the individual spectral bands is used to enhance the textual information. An evolutionary optimizer is considered to obtain the optimal and some suboptimal 3-band subspaces from which an ensemble of experts is then formed. The framework is applied to a ground truth multispectral dataset with promising results. In addition, a generalization to the cross-validation approach is developed that not only evaluates generalizability of the framework, it also provides a practical instance of the selected experts that could be then applied to unseen inputs despite the small size of the given ground truth dataset.