Undithering using linear filtering and non-linear diffusion techniques

TL;DR

This paper introduces an undithering method that combines linear filtering and anisotropic diffusion to reconstruct gray images from binary dithered images, improving gray value reproduction.

Contribution

The proposed approach uniquely integrates linear filtering with anisotropic diffusion for effective undithering of binary images.

Findings

Reconstructed images retain many original gray values.

The method enhances edges while smoothing.

Reconstructed images are less sharp but preserve key gray levels.

Abstract

Data compression is a method of improving the efficiency of transmission and storage of images. Dithering, as a method of data compression, can be used to convert an 8-bit gray level image into a 1-bit / binary image. Undithering is the process of reconstruction of gray image from binary image obtained from dithering of gray image. In the present paper, I propose a method of undithering using linear filtering followed by anisotropic diffusion which brings the advantage of smoothing and edge enhancement. First-order statistical parameters, second-order statistical parameters, mean-squared error (MSE) between reconstructed image and the original image before dithering, and peak signal to noise ratio (PSNR) are evaluated at each step of diffusion. Results of the experiments show that the reconstructed image is not as sharp as the image before dithering but a large number of gray values are reproduced with reference to those of the original image prior to dithering.