Improving Quantization Matrices for Image Coding by Machine Learning

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

We investigate the generation of quantization matrices for image coding in the scenario to balance compression ratio and quality. We make use of machine learning to train and determine those quantization matrices that can achieve the best compression ratio while reaching the quality settings. By introducing the trainable parameters and considering the impact of the quantization module on task performance and compression ratio, the DCT and quantization modules are jointly optimized to minimize the total coding cost. We evaluate the well-trained quantization matrices under various quality settings of JPEG. The results indicate that the proposed scheme can be combined with quality settings to consistently achieve better compression performance.

原文English
主出版物標題ICDSP 2022 - 2022 6th International Conference on Digital Signal Processing
發行者Association for Computing Machinery
頁面115-119
頁數5
ISBN(電子)9781450395809
DOIs
出版狀態Published - 25 2月 2022
事件6th International Conference on Digital Signal Processing, ICDSP 2022 - Virtual, Online, China
持續時間: 25 2月 202227 2月 2022

出版系列

名字ACM International Conference Proceeding Series
Par F180471

Conference

Conference6th International Conference on Digital Signal Processing, ICDSP 2022
國家/地區China
城市Virtual, Online
期間25/02/2227/02/22

指紋

深入研究「Improving Quantization Matrices for Image Coding by Machine Learning」主題。共同形成了獨特的指紋。

引用此