摘要
利用近似正交变换——双正交变换的特殊性质,提出了一种新的图像镶嵌方法.当高低通滤波器长度为奇数且关于0对称时,运用新的边界延拓方式,解决了滤波器长度越大,拼接效果越好但边界恢复效果不理想的问题,使得图像能够精确重构.仿真试验证明了该方法的有效性.
By using the special characteristics of the analogical orthogonal transformation, biorthogonal wavelet transformation,a new method of image merging is presented.Under the conditions that high-pass fiter and low-pass filter all have an odd number of non-zero samples and are symmetric about zero,there is a problem that the length of filter is bigger, the result of merging is better,but the boundary reconstruction is not satisfied.The problem is solved and the image is reconstructed precisely by using a new boundary extension method in this paper.The validity of the method is illustrated by the simulation results.
出处
《应用数学》
CSCD
北大核心
2007年第S1期139-142,共4页
Mathematica Applicata
关键词
双正交小波变换
图像镶嵌
边界延拓
重构
Biorthogonal wavelet transformation
Image merging
Boundary extension
Reconstruction