Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks

TL;DR

This paper applies deep convolutional neural networks to solve traditional low-level image processing problems, specifically companding and inverse halftoning, demonstrating the effectiveness of deep learning in these areas.

Contribution

It is the first to develop deep learning solutions for companding and inverse halftoning, leveraging CNNs for nonlinear image transformation and feature extraction.

Findings

Deep CNNs effectively improve image quality in companding and inverse halftoning.

The proposed methods outperform traditional approaches in experimental tests.

Deep learning models capture visually important features for image enhancement.

Abstract

In this paper, we introduce deep learning technology to tackle two traditional low-level image processing problems, companding and inverse halftoning. We make two main contributions. First, to the best knowledge of the authors, this is the first work that has successfully developed deep learning based solutions to these two traditional low-level image processing problems. This not only introduces new methods to tackle well-known image processing problems but also demonstrates the power of deep learning in solving traditional signal processing problems. Second, we have developed an effective deep learning algorithm based on insights into the properties of visual quality of images and the internal representation properties of a deep convolutional neural network (CNN). We train a deep CNN as a nonlinear transformation function to map a low bit depth image to higher bit depth or from a halftone image to a continuous tone image. We also employ another pretrained deep CNN as a feature extractor to derive visually important features to construct the objective function for the training of the mapping CNN. We present experimental results to demonstrate the effectiveness of the new deep learning based solutions.