基于非降采样Contourlet的单帧图像超分辨率算法  

Single Frame Super Resolution Reconstruction Based on Nonsubsampled Contourlet Transform

作　　者：张威[1] 陈微[1] 

机构地区：[1]北华大学计算机科学计算机学院,吉林吉林132021

出　　处：《微电子学与计算机》2013年第12期73-76,共4页Microelectronics & Computer

基　　金：吉林市杰出青年项目(201162501);吉林省教育厅十二五重点科技项目(2013161)

摘　　要：为了实现单帧图像边缘纹理保持的超分辨率重建,提出一种基于非降采样Contourlet(NSCT)的单帧图像超分辨率算法.对原始低分辨率图像进行NSCT变换后,采用基于边缘方向的插值方法把高频子带图像放大至目标分辨率,计算各方向子带的噪声判别阈值,对系数进行增强处理,得新的子带系数图像.对原始低分辨率图像采用双线性插值方法放大后替代低频子带系数,再经过逆NSCT变换得到高分辨率图像,实验结果表明,相比其他传统的超分辨率方法,此算法边缘平滑、图像结构失真小,噪声抑制效果好.In order to preserve the texture and edge information and to improve the space resolution of single frame, a novel super resolution reconstruction was proposed by using Nonsubsampled Contourlet transformation and interpolation method based on edge direction. The image is transformed into the high-pass sulyband and low-pass sub-band by NSCT. The threshold is set in the high-pass sub-band, the high-pass sub-band coefficients is enhanced and de-noised, and low-frequency components are replaced by the enhanced amplitude of the original image. A high- resolution image is achieved by inverse NSCT. The experimental results indicate that, compared with traditional super resolution reconstruction algorithms, this algorithm can get smooth edges and recovery the texture features, and resist Gaussian noise.

关 键 词：NSCT 图像插值 超分辨率重建 图像增强 图像去噪 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]