基于周期延拓的纯二维小波变换  

True 2-D wavelet transform based on periodic extension

作　　者：王静[1] 徐妮妮[1] 杨雪玲[1] 

机构地区：[1]天津工业大学电子与信息工程学院,天津300387

出　　处：《天津工业大学学报》2012年第2期69-73,共5页Journal of Tiangong University

基　　金：国家自然科学基金资助项目(60602036)

摘　　要：研究了周期延拓在纯二维小波变换中的应用,给出了原始像块最大分解级数和各级像块支撑区的确定方法.原始像块的行数和列数不拘泥于2n,可以是任意整数,其左上角行列坐标可以是奇数或偶数的任意组合,小波分解域数据量等于或略大于原始像块的数据量,若忽略有限精度问题,可以实现数据的完全重构.以纯二维5/3小波变换为例,给出了小波分解与重构规程.The application of the period extension in a true 2-D wavelet transform is studied,and the methods for determining the maximum decomposition level and sizes of every level of block are given.The original block of row or column length is not limited to 2n,it can be any integer,and the row and column coordinate of the upper left corner of the image data can be any combination of odd and even.The data of wavelet decomposition is equal to or slightly larger than the original block.If ignoring the problem of limited accuracy,the data can be completely reconstructed.Taking true 2-D 5/3 wavelet transform as an example,the wavelet decomposition and reconstruction procedures are given.

关 键 词：周期延拓 纯二维小波变换 分解级数 

分 类 号：TN911.7[电子电信—通信与信息系统]