Sturdy Binarization Method to Enhance Historic Document Images

Abstract: In this paper, a sturdy binarization model for historic documents and manuscripts is proposed, The three main steps in this proposed method are: preprocessing, main binarization, and post-processing. The preprocessing step mainly involves image denoising followed by some morphological operations. Then, we use the phase congruency features for the main binarization step. After completing the binarization steps on the input images using phase congruency features and a denoised image, finally the enhancement processes are applied as post-processing. The complete experimental consequences on different data sets display the sturdiness of the proposed binarization method on diverse kinds of degradation and document images.

Keywords: Binarization, phase congruency features, document enhancement, robustness.