학습-기반 이미지 손실 압축 기법에 대한 연구

Abstract

Image compression is a fundamental technique in the field of digital image processing, which will help to decrease the storage space and to transmit the files efficiently. Compression of images is necessary due to bandwidth and memory constraints. Helpful, redundant, and irrelevant information are three different forms of information found in images. Recently many learning-based techniques have been proposed to promise results on image compression field. This paper surveys recent techniques utilizing mostly lossy image compression using machine learning architectures. The majority of the publications in the compression domain surveyed are from the previous five years and use a variety of approaches.