Confidence Score for Unsupervised Foreground Background Separation of Document Images

TL;DR

This paper introduces a new method to compute confidence scores for unsupervised foreground-background separation in document images, enhancing the interpretability and utility of binarization algorithms without increasing computational complexity.

Contribution

The paper presents a novel approach for confidence scoring in unsupervised document image binarization that maintains the same computational complexity as existing methods.

Findings

Confidence scores improve document binarization quality.

Scores assist in document cleanup and texture addition tasks.

Method is computationally efficient and compatible with existing algorithms.

Abstract

Foreground-background separation is an important problem in document image analysis. Popular unsupervised binarization methods (such as the Sauvola's algorithm) employ adaptive thresholding to classify pixels as foreground or background. In this work, we propose a novel approach for computing confidence scores of the classification in such algorithms. This score provides an insight of the confidence level of the prediction. The computational complexity of the proposed approach is the same as the underlying binarization algorithm. Our experiments illustrate the utility of the proposed scores in various applications like document binarization, document image cleanup, and texture addition.