一种基于零树小波的图像比率可分级编码方法的研究  

Research on Rate Scalable Image Coding Based on Zerotree Wavelet

作　　者：王相海[1] 张福炎[1] 

机构地区：[1]南京大学计算机软件新技术国家重点实验室南京大学计算机科学与技术系,南京210093

出　　处：《南京大学学报（自然科学版）》2002年第2期145-151,共7页Journal of Nanjing University（Natural Science）

基　　金：南京大学计算机软件新技术国家重点实验室资助

摘　　要：Shapiro的EZW算法具有可产生嵌入式码流、可精确控制压缩比等特点 ,倍受人们的关注 .然而该算法还有一些不足 ,如在进行零树编码时 ,对未被包括进零树的“零值” ,需要将其编成“孤立零”码 ,试验表明这部分编码通常占有较高的代价 ,往往会影响到编码效率 .在分析了EZW编码过程和码流的基础上 ,提出一种阶梯型量化和零树小波相结合的图像比率可分级性编码方法 .首先对图像小波分解的较低级子带的变换系数采取一种阶梯型量化 ,然后对整体小波系数采用零树编码 ,并利用逐次逼近量化方法获得潜入式码流 ,以实现比率的可分级解码 .它在一定程度上克服了EZW算法的不足 ,提高了PSNR值 .Embedded Zerotree wavelet (EZW) image coding algorithm, introdeced by J.M.Shapiro, is of great interest for many researchers because it can produce an embedded bit stream and it runs sequentially and stops whenever a target bit rate or a target distortion is met. However, there are still several deficiencies, one of which is that the arbitrarily shaped zeros are encoded using the highly constrained zerotrees. Some zeros that cannot be included in zerotrees have to be encoded individually as isolated zeros, and the cost is very high. In this paper, an image rate scalable coding algorithm based on scalar quantization and zerotree wavelet is proposed, in which a scalar quantization is first adopted on the wavelet transformation coefficients in the low scale subbands, and the successive_approximation quantization and EZW algorithm are used in order to produce an embedded bit stream. Simulation results show the proposed coding scheme is simple in structures and is superior to the EZW algorithm in PSNR.

关 键 词：零树小波 EZW算法 阶梯型量化 小波变换 图像比率可分级编码 图像编码 逐次逼近量化 

分 类 号：TN919.81[电子电信—通信与信息系统]