arrow
返回

Image Coding With Data-Driven Transforms: Methodology, Performance and Potential

delete2020-01-01
delete14
PRE
AI
X
Xinfeng Zhang *
C
Chao Yang
X
Xiaoguang Li
S
Shan Liu
H
Haitao Yang
I
Ioannis Katsavounidis
S
Shawmin Lei
C
C.‐C. Jay Kuo
DOI:10.1109/TIP.2020.3025203delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Image compression has always been an important topic in the last decades due to the explosive increase of images. The popular image compression formats are based on different transforms which convert images from the spatial domain into compact frequency domain to remove the spatial correlation. In this paper, we focus on the exploration of data-driven transform, Karhunen-Loeve transform (KLT), the kernels of which are derived from specific images via Principal Component Analysis (PCA), and design a high efficient KLT based image compression algorithm with variable transform sizes. To explore the optimal compression performance, the multiple transform sizes and categories are utilized and determined adaptively according to their rate-distortion (RD) costs. Moreover, comprehensive analyses on the transform coefficients are provided and a band-adaptive quantization scheme is proposed based on the coefficient RD performance. Extensive experiments are performed on several class-specific images as well as general images, and the proposed method achieves significant coding gain over the popular image compression standards including JPEG, JPEG 2000, and the state-of-the-art dictionary learning based methods.
Keyword:
Image coding
Transform coding
Kernel
Quantization (signal)
Discrete cosine transforms
Dictionaries
Image compression
Karhunen-Loeve transform (KLT)
principal component analysis (PCA)
data-driven transform
rate-distortion optimization
adaptive quantization
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Image Processing 封面图
IEEE Transactions on Image Processing
IF:
13.7
论文数:
1.0W
被引数:
8.4W

机构

N
netflix, inc.
学者数:
46
论文数: 45
被引数: 0
U
university of chinese academy of sciences, cas
学者数:
4.1W
论文数: 3.8W
被引数: 75
U
university of southern california
学者数:
4.7W
论文数: 3.8W
被引数: 51
F
facebook inc
学者数:
588
论文数: 381
被引数: 0
B
Beijing University of Technology
学者数:
2.8W
论文数: 2.1W
被引数: 2.7W
S
shanghai university
学者数:
3.9W
论文数: 2.7W
被引数: 52
C
chinese academy of sciences
学者数:
56.7W
论文数: 45.0W
被引数: 704
学者 查看更多机构
引用论文

引用论文

err分享
err收藏
Simultaneous MS-IR Studies of Surface Formate Reactivity Under Methanol Synthesis Conditions on Cu/SiO2
err2009-06-09
err0
PREAI
errY. Yang; C. A. Mims; R. S. Disselkamp; C. H. F. Peden; C. T. Campbell
err分享
err收藏
Remote sensing the magnetosphere using ground-based observations of ULF waves
err2006-01-01
err0
PREAI
errC. L. Waters; F. W. Menk; M. F. Thomsen; C. Foster; F. R. Fenrich
err分享
err收藏
学者 查看更多内容