摘要
研究了小波变换用于图像压缩涉及到的小波系数阈值的确定问题.建立了评价图像小波变换后各层子图像能量分布的理论公式;给出了确定小波系数阈值的方法和一种新的图像压缩算法.以典型的Lena图像为例,在同等压缩比条件下,把本文提出的图像压缩方法与FFT和DCT法进行了对比,结果表明:本方法有明显的图像改善效果和抗"分块效应"的能力.
How to determine the thresholds of simplifying wavelet coefficients for an image with different resolutions is discussed .A set of theoretical expressions are developed to analyze the energy of images transformed with different resolutions. Taking the maximum energy of the image under every resolution as a compression factor, a method of determining the thresholds applied to cull wavelet coefficients for the image is presented, and a new image compression algorithm is constructed as well. An experiment of compressing the Lena picture is done, based on our new method, FFT and DCT, respectively, under the same image compression rate. All the results have shown that the new method is better than FFT and DCT in improving upon the quality and the visual effect of the compressed image.
出处
《哈尔滨工程大学学报》
EI
CAS
CSCD
2003年第5期556-559,共4页
Journal of Harbin Engineering University
关键词
小波变换
多分辨率分析
图像压缩
能量分布
wavelet transform
multi-resolution analysis
image compression
energy distribution