Unsupervised ensemble of experts (EoE) framework for automatic binarization of document images

TL;DR

This paper introduces an ensemble framework for document image binarization that intelligently combines multiple methods based on confidence and expert grouping, improving robustness and performance across benchmarks.

Contribution

The proposed EoE framework uniquely incorporates confidence, endorsement, and expert grouping to enhance ensemble binarization of document images, with a novel selection process and weighting scheme.

Findings

Effective combination of binarization methods on H-DIBCO'12 dataset

Improved binarization performance over individual methods

Versatile framework adaptable to different ensembles

Abstract

In recent years, a large number of binarization methods have been developed, with varying performance generalization and strength against different benchmarks. In this work, to leverage on these methods, an ensemble of experts (EoE) framework is introduced, to efficiently combine the outputs of various methods. The proposed framework offers a new selection process of the binarization methods, which are actually the experts in the ensemble, by introducing three concepts: confidentness, endorsement and schools of experts. The framework, which is highly objective, is built based on two general principles: (i) consolidation of saturated opinions and (ii) identification of schools of experts. After building the endorsement graph of the ensemble for an input document image based on the confidentness of the experts, the saturated opinions are consolidated, and then the schools of experts are identified by thresholding the consolidated endorsement graph. A variation of the framework, in which no selection is made, is also introduced that combines the outputs of all experts using endorsement-dependent weights. The EoE framework is evaluated on the set of participating methods in the H-DIBCO'12 contest and also on an ensemble generated from various instances of grid-based Sauvola method with promising performance.