摘要
提出了一种基于小波变换的矢量量化方法，有效地利用了小波变换的空间分辨率，并结合将级间对应区域中系数小于某一阈值的矢量看作零矢量的熵编码技术．实验表明上述方法可达到高效压缩效果．
This paper proposed a vector quantization based on wavelet decomposition. It can effectively exploit the space resolution of wavelet decomposition. When a vectors all coefficients are below a threshold, We call it a zerovector and utilize a entropy coding. The experiment result shows that this method can achieve a good compression effect.
出处
《兰州铁道学院学报》
1998年第2期43-47,共5页
Journal of Lanzhou Railway University
基金
甘肃省自然科学基金
关键词
小波变换
矢量量化
神经网络
图像压缩
wavelet transform
vector quantization
neural network
arithmetic coding
