基于小波域的压缩感知超分辨率重建方法

Super-resolution Reconstruction Method Based on Wavelet Domain and Compressive Sensing

为了提高超分辨率图像的重构效果,提出了一种基于小波域的压缩感知超分辨率重建方法。首先采用小波变换对低分辨率图像进行分解,得到低分辨率图像的低频子带与高频子带,然后采用压缩感知技术分别对低频子带和高频子带进行重建,并通过小波逆变换得到最终重建图像,最后在MATLAB 2012平台上进行仿真实验。结果表明,相对于其他图像重建方法,本文方法的重建图像视觉效果更加理想,不仅提高了低分辨率图像重建精度,而且提高了图像重建效率,可以满足图像处理的实时性、在线性要求。

In order to improve the effect of image super-resolution reconstruction, a super-resolution reconstruction method based on wavelet domain and compressive sensing is proposed in this paper, Firstly, wavelet transform is used to decompose the low reso- lution images and get the low frequency and high frequency sub bands, and then the low resolution frequency sub bands and the high frequency sub bands of image are reconstructed respectively by compressed sensing and get the final image reconstructed by the wavelet inverse transform. Finally,the simulation experiments are carried out to test performance on the platform of MATLAB 2012. The results show that, com with other image reoenstruction methods, the proposed method not only can obtain better re- construction image visual effect, enhance the low resolution image reconstruetion quality, but also improve the efficiency of image reconstruction, can meet the real-time, online requirement of image processing.