【摘要】 研究了一种图像压缩方法,首先对图像进行小波分解,然后依据小波系数的统计特性和分布特点,对不同的子图像块采用不同的量化、编码方法。针对低分辨率子图像,先经DCT变换,再采用线性预测编码(DPCM);而对高分辨率子图像采用基于Kohonen网络的自组织特征映射(SOFM)算法进行矢量量化。实验证明,上述图像压缩方法可以在保证重构图像质量良好的情况下,获得较大的压缩比。更多还原

【Abstract】 This paper presents an image compression scheme, which uses the wavelet transform and neural network. First, after the image is decomposed at different scales by using the wavelet transform, the different quantization and coding schems for each subimage are carried out in accordance with its statistical properties and distributed properties of the coefficients. The wavelet coefficients in low frequency subimage is transformed by DCT before they are compressed by using DPCM. The wavelet coefficients in high frequency subimages are compressed and vector quantized by using Kohonen neural network on SOFM algorithm. Using these compressing techniques, we can obtain rather satisfactory compression ratio while achieving superior reconstructed images.更多还原