论文部分内容阅读
目的研究小波变换和分形编码在图像数据压缩中的应用．方法根据小波变换后不同分辨率下图像的子带小波系数的相似性，通过分形非收缩仿射变换，利用低一级频率分辨的子带小波系数子树预测高一级频率分辨的子带小波系数子树，实现对图像的高效描述．结果实验结果表明，该方法可在保证一定图像质量的条件下，获得较大的图像压缩比（例如，当峰值信噪比ＰＳＮＲ＝２９．０８ｄＢ时，压缩比ｃｒ＝７４．８）．结论该方法可充分发挥小波变换和分形编码的优势，为低比特率图像压缩提供新的思路．
Aim To study the application of wavelet transform and fractal coding in image data compression. Methods Based on the similarity of subband wavelet coefficients of images under different resolutions after wavelet transform, subband wavelet of higher order frequency resolution is predicted by sub-band wavelet coefficient sub-tree of lower-order frequency resolution by fractal non-shrinking affine transformation Coefficient sub-tree, to achieve an efficient description of the image. Results The experimental results show that the proposed method can obtain a large image compression ratio (for example, cr = 74.8 when the peak PSNR = 29.08dB) with a certain image quality. Conclusion This method can give full play to the advantages of wavelet transform and fractal coding and provide a new idea for low bit rate image compression.