基于各向异性的快速超分辨率图像重建

针对传统超分辨率图像重建算法速度慢的缺点,提 出了一种基于自适应各向异性正则化的快速超分辨率图像重建算法。本文 算法兼顾重建图像质量的同时,提升了图形的重建速度。基于传统迭代算法,本文算法通过 优化约束条件,大量剔除了冗余过程, 弥补了传统算法的不足；同时引入一种具有自适应能力的各向异性平滑项,可以适应各种 复杂的运动模型。另外,提出 以图像的峰值信噪比(PSNR)为标准,作为重建迭代的截止 条件。运 用本文算法对序列低分辨率图像进行重建,证明了本文算法可以更快实现超分辨率图像重 建。

Fast super-resolution image reconstruction based on anisotropic term

A fast super-resolution reconstruction algorithm based on adaptive anisotropic regularization is proposed to overcome the low speed of traditional super-resolution reconstruction algorithms.This al gorithm can improve the speed of image reconstruction,while the quality of the i mage is also reconstructed very well.Based on the traditional iterative model,th e constraint condition is optimized,and the redundant processes are deleted to a void the disadvantages of traditional methods.A adaptive anisotropic smoothing t erm is proposed ot preserve the sharper edges effectively. In addition,the cut-off condition of reconstructed iteration is proposed based on the peak signal-to-noise ratio (P SNR) of the image.Th e algorithm is applied to reconstruct the sequence low- resolution image,and it is proved that the algorithm can realize the super-r esolution reconstruction more quickly.