A maximal-information color to gray conversion method for document images: Toward an optimal grayscale representation for document image binarization

TL;DR

This paper introduces a novel color-to-gray conversion method that enhances document image binarization by maximizing information retention and selecting optimal gray representations, improving contrast and readability.

Contribution

The proposed dual transform method optimally balances color channel information for improved document binarization, incorporating a homogeneity-based channel selection and color reduction preprocessing.

Findings

Enhanced binarization performance on multiple datasets

Improved contrast and readability in grayscale images

Effective color reduction and channel selection strategy

Abstract

A novel method to convert color/multi-spectral images to gray-level images is introduced to increase the performance of document binarization methods. The method uses the distribution of the pixel data of the input document image in a color space to find a transformation, called the dual transform, which balances the amount of information on all color channels. Furthermore, in order to reduce the intensity variations on the gray output, a color reduction preprocessing step is applied. Then, a channel is selected as the gray value representation of the document image based on the homogeneity criterion on the text regions. In this way, the proposed method can provide a luminance-independent contrast enhancement. The performance of the method is evaluated against various images from two databases, the ICDAR'03 Robust Reading, the KAIST and the DIBCO'09 datasets, subjectively and objectively with promising results. The ground truth images for the images from the ICDAR'03 Robust Reading dataset have been created manually by the authors.