Convolutional Neural Network (CNN) to reduce construction loss in JPEG compression caused by Discrete Fourier Transform (DFT)

TL;DR

This paper proposes a CNN-based autoencoder approach to improve JPEG image compression by reducing artifacts caused by DFT, achieving better reconstruction quality and efficient feature extraction.

Contribution

It introduces a novel CNN autoencoder method specifically designed to mitigate DFT-induced artifacts in JPEG compression, enhancing image quality.

Findings

Improved image reconstruction quality.

Effective reduction of DFT-related artifacts.

Autoencoders enable better compression and visual quality.

Abstract

In recent decades, digital image processing has gained enormous popularity. Consequently, a number of data compression strategies have been put forth, with the goal of minimizing the amount of information required to represent images. Among them, JPEG compression is one of the most popular methods that has been widely applied in multimedia and digital applications. The periodic nature of DFT makes it impossible to meet the periodic condition of an image's opposing edges without producing severe artifacts, which lowers the image's perceptual visual quality. On the other hand, deep learning has recently achieved outstanding results for applications like speech recognition, image reduction, and natural language processing. Convolutional Neural Networks (CNN) have received more attention than most other types of deep neural networks. The use of convolution in feature extraction results in a less redundant feature map and a smaller dataset, both of which are crucial for image compression. In this work, an effective image compression method is purposed using autoencoders. The study's findings revealed a number of important trends that suggested better reconstruction along with good compression can be achieved using autoencoders.