基于小波变换和自适应标矢量混合量化的图像压缩

Image Compression based on Wavelet Transform and Adaptive Scalar - Vector Hybrid Quantization

提出了一种基于小波变换和自适应标矢量混合量化的图像压缩技术.该算法首先将图像分成不同层次不同频率的子带,对含能量大的低频子带采用无失真的DPCM编码;利用相同方向不同尺度子带之间的相关性,对其余的高频子带利用自组织特征映射神经网络进行矢量量化编码,实验证明:此方法兼顾了图像的压缩比、编解码时间以及重构图像质量等因素.

IIn this paper, a new method of image compression based on wavelet transform and adaptive scalar - vector hybrid quantization is presented. Firstly, the image is decomposed into a series of different frequency subimages by wavelet transform. Then, the lowest -frequency subimage which contains the most information of the image is encoded by using the method of DPCM coding, and the rest higher frequency subimages undergoes quantization by using self - organizing feature map neural network according to the sim...