摘要
在传统凸集投影(POCS)算法基础上,考虑到算法对于初始图像的依赖性,尝试通过引入近似点扩散函数检测(APEX)盲解卷积技术,对POCS算法的初始参考图像进行盲恢复,然后再进行超分辨率图像重建。仿真实验证明,APEX盲恢复后的初始图像,相比原初始图像,更加接近真实图像。重建后,直观上图像的清晰度有了一定程度的提高,由于更好地抑制了噪声,表现在PSNR有了一定的提升;另外,由于APEX的引入,改进算法在一定程度上降低了原算法对初值的依赖程度,增强了POCS算法的鲁棒性。
Based on the traditional algorithm-Projection onto convex sets（POCS）,we considered the dependence on the initial image of the traditional projection onto convex set（POCS） and tried to introduce approximate point spread function examining（APEX） blind deconvolution technology in order to restore the initial one blind from reference image for image super-resolution reconstruction based traditional POCS algorithm.Simulation experiment results proved that Initial image after the APEX blind deconvolution,compared with the original initial image,were closer to the real image.Images have a certain degree increase on the clarity visually after reconstruction and due to suppressing the noise,the PSNR of reconstruction image increased;in addition,due to the introduction of the APEX,the improved algorithm reduced the reliance of the initial value in the original algorithm to a certain extent and enhanced the POCS algorithm robustness.
出处
《电子测量技术》
2012年第5期63-65,共3页
Electronic Measurement Technology
关键词
超分辨率重建
凸集投影(POCS)
盲解卷积
非线性最小二乘拟合
近似点扩散函数检测(APEX)
super-resolution reconstruction
projection onto convex sets（POCS） blind deconvolution
non-linear least squares fitting
approximate point spread function examining（APEX）
