Cache-efficient wavelet lifting in JPEG 2000

被引:17
作者
Chatterjee, S [1 ]
Brooks, CD [1 ]
机构
[1] IBM Corp, Thomas J Watson Res Ctr, Yorktown Hts, NY 10598 USA
来源
IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOL I AND II, PROCEEDINGS | 2002年
关键词
D O I
10.1109/ICME.2002.1035902
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The Discrete Wavelet Transform (DWT), the technology at the heart of the JPEG 2000 image compression system, operates on user-definable tiles of the image, as opposed to fixed-size blocks of the image as does the Discrete Cosine Transform (DCT) used in JPEG. This difference reduces artificial blocking effects but can severely stress the memory system. We examine the interaction of the DWT and the memory hierarchy, modify the structure of the DWT computation and the layout of the image data to improve cache and TLB locality, and demonstrate significant performance improvements of the DWT over a baseline implementation. Our optimized DWT implementation exhibits speedups of up to 4x over the DWT in a JPEG 2000 reference implementation.
引用
收藏
页码:797 / 800
页数:4
相关论文
共 15 条
[1]   Image coding using wavelet transform [J].
Antonini, Marc ;
Barlaud, Michel ;
Mathieu, Pierre ;
Daubechies, Ingrid .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1992, 1 (02) :205-220
[2]  
CHATTERJEE S, 1999, P 1999 ACM INT C SUP, P444
[3]  
Chatterjee S., 2000, P 6 INT S HIGH PERFO, P195
[4]   Line-based, reduced memory, wavelet image compression [J].
Chrysafis, C ;
Ortega, A .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2000, 9 (03) :378-389
[5]  
CMELIK RF, 1994, P 1994 ACM SIGMETRIC, P128
[6]  
*ISO IEC, 2001, 1SC JTC ISOIEC
[7]  
*ISO IEC, 1997, 1SC JTC ISOIEC
[8]  
LEGALL D, 1988, P INT C AC SPEECH SI, P761
[9]  
MEERWALD P, 2002, P SPIE EL IM VIS COM, V4671
[10]  
NELSON M, 1989, DOBBS J OCT, P29