基于小波和匹配跟踪的分层图像编码算法  

Multi-Layered Image Coding Based on Wavelet and Matching Pursuit Transforms

作　　者：刘利雄[1] 廖斌[2] 贾云得[1] 王元全[1] 

机构地区：[1]北京理工大学计算机科学技术学院,北京100081 [2]华北电力大学电气与电子工程学院,北京102206

出　　处：《北京理工大学学报》2007年第10期891-895,共5页Transactions of Beijing Institute of Technology

基　　金：国家自然科学基金资助项目(60473049;60602050)

摘　　要：提出了一种基于小波和匹配跟踪的分层图像编码算法.该算法将原始图像划分成包含不同结构特征的平滑边缘层和纹理层,采用不同的压缩算法对不同的图像层进行编码,从而达到对整幅图像最优编码的目的.实验结果表明,该算法不仅能够有效地捕捉图像中所包含的边缘和纹理等具有高频窄带的信号特征,而且在极低位率下的重建图像质量要优于单一小波图像编码算法.Proposes a new multi-layered image coding algorithm based on wavelet and matching pursuit transforms. The original image is divided into smooth edge layer and texture layer, and in each layer different compression algorithms are adopted for coding. As a result, the aim of coding whole image can be achieved optimally. Experiments showed that it can capture texture and edge characteristics efficiently and the quality of reconstructed image is better than traditional single wavelet image coding algorithm at low bit rates.

关 键 词：小波变换 分层图像 图像编码 匹配跟踪 纹理编码 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]