一种有效的超分辨率图像序列重建算法

Effective Super-resolution Image Sequence Reconstruction Algorithm

针对降质图像序列的超分辨率重建研究,分析了超分辨率重建问题中图像序列的降质过程和重建过程的不适定问题,并提出了用最小二乘法和自适应正则化结合分布迭代的方法对图像序列进行重建.实验结果表明,该方法可以有效重建出高分辨率图像,在复原图像的峰值信噪比和主观视觉效果等方面比其他方法都有显著的提高.

Aiming at the reconstruction of degraded image sequence super-resolution, this paper analyzes image sequence degraded process and reconstruction process of ill-posed problem in super- resolution reconstruction. It is put forward that the method of least square method, adaptive regurnization and distribution iteration be used to reconstruct image sequence. The experimental results show that this method can effectively reconstruct super-resolution images, and the SNR of the reproduced image at peak and the subjective vision effect are significantly improved.