摘要
鉴于自然物体图像具有分形特征 ,提出了小波分形插值应用于遥感图像处理的新方法 这种小波分形插值方法利用小波变换系数中低分辨率频带中的高频分量相似高分辨率频带中的高频分量的特点 将遥感图像在小波变换的基础上用分形做相似变换 ,进而通过反变换得到比原图像分辨率高的插值图像 实验证明 ,小波分形插值方法比现有的双线性插值。
Considering that the image of natural scenery has fractal character, a wavelet fractal interpolation algorithm is presented, which is applied in remote sensing image processing. The wavelet transform processes the high frequency information and the low frequency information simultaneously, which is like the human visual system. The fractal interpolation algorithm can preserve the texture information of image. So, the wavelet fractal interpolation algorithm uses fractal interpolation algorithm to anticipate the high frequency part on high resolution from the high frequency part on low resolution. It has been found that this new wavelet fractal interpolation has better performance than the existing bilinear interpolation algorithm.
出处
《计算机研究与发展》
EI
CSCD
北大核心
2005年第2期247-251,共5页
Journal of Computer Research and Development
基金
国家自然科学基金项目 (60 2 72 0 5 6
90 3 0 40 0 3 )
国家"十五"基础基金项目 (k2 0 0 40 60 42 0 )
关键词
小波变换
分形
小波分形插值
遥感图像处理
wavelet transform
fractal
wavelet fractal interpolation
remote sensing image processing
