基于分割的并行图像压缩方法研究

Parallel Algorithms for Image Coding Based on Unbalance Segmentation

给出一种基于非均匀分割的并行图象压缩方法。系统的研究了传统图象分割方法[1～3]，为了提高图象编码速度，给出了一种在不降低压缩比条件下的并行分割压缩方法润时，还给出一种确定分割阀值的新方法--累积2乘误差方法，使生成图像的信噪比提高了1-2dB。

A parallel algorithms is given for image coding based on unbalance segmentation.Image is splited into rectangle (sub-block) that is not equal. The grey value of points in sub-block is bordered with vertex interpolation. The authors improve classical segmentation methods, and give a parallel algorithms and a new to assign splitting condition, get a more speed in image compression and a better quality of reconstruction .