基于区域和边缘分开编码可伸缩彩色图像编码

Region and edge segmentation-based highly scalable coding method on color image

提出了一种基于区域和边缘分开编码的可伸缩彩色图像编码算法,该算法采用按各区域重要性程度分别进行不同精度的编码,并采用MEZW方法组织码流。算法分三步:一是将图像分割为纹理均一或表示独立意义的区域,并按重要程度分别排序;二是对各区域边缘像素进行DCT和小波变换;三是采用MEZW对小波系数进行处理并复合为输出码流。

A region and edge segmentation-based highly scalable coding method on color image has been presented. The algorithm is divided into three sequential steps. The first step is that the color image is segmented as homogeneous texture region or independent object. The second step includes DCT transform of edge pixels and wavelet transform of individual region. The third step is to output layered code stream after the wavelet coefficients is organized by MEZW method.