基于非局部POCS的超分辨率图像重建

Super-resolution Image Reconstruction Based on Non-local POCS

图像获取过程中,受成像系统的影响,无法获取原始场景中所有的信息。超分辨率图像重建技术就是在不改变成像系统的前提下,提高图像质量。POCS(凸集投影算法)可以利用多帧低分辨率图像重建一帧高分辨率图像。然而传统的POCS算法通常会产生"锯齿"边缘。在自然图像中,会存在许多的相似边缘结构。利用局部相似性的结构,可以有效地消除"锯齿"边缘。因此提出一种基于非局部POCS的超分辨率图像重建算法,以有效锐化图像边缘,提高图像的视觉感观。

Image acquisition process, affected by the imaging system, cannot get all the information of the original scene. Super-resolution image reconstruction is the technique to boost image quality under the premise of not changing the imaging system. POCS （proj ection onto convex sets algorithm） can take advantage of multi-frame low-resolution ima- ge to reconstruct a high resolution image. However, the traditional POCS algorithm usually produces the ＂jaggy＂ edge. In nature images, there will be many similar-edge structure. Taking advantage of local similarity structure can effectively eliminate the ＂jaggy＂ edge. Therefor a non-local POCS-based super-resolution image reconstruction algorithm was pro- posed. It can sharpen image edge effectively, and improve the visual senses of the image.