一种基于显著不相关检验的快速分形图像编码方法

A Fast Fractal Image Coding Based on Testing Significant Uncorrelation of Blocks

针对分形编码计算量过大的缺点，本文提出一种基于显著不相关检验的分形编码方法。对于文中的测试图像（Lenn256×256×8ppb和Boat256×256×8ppb），其编码速度比基于子块分类的分形编码方法快2～15倍，而解码图像质量（PSNR）没有明显下降，压缩比还有一定的提高。

To overcome drawbacks of fractal image coding,such as highly computational complexity,we proposed a fast fractal image coding method,which is based on tests of significant uncorrelation of blocks.For the test images(Lenna 256×256×8ppb and Boat 256×256×8ppb),comparing with other fractal image coding methods based on classification of blocks,we record acceleration factors from 2 up to 15 with negligible or minor degradation in PSNR and some improvement of the compression ratio.