摘要
为了解决稀疏信号的重建问题提出了光滑e0范数优化算法,它与最小1范数优化算法等图像重建的方法相比有很大的不同,着重实验了这种信号重建算法中重要参数的选择,并利用手写体数字图像库为试验样本做了一维信号重建和二维图像重建实验.实验结果证明了基于e0范数优化算法在图像重建时间和重建精度上的优越性,此为后续的图像工程研究奠定了基础.
In order to solve the problem of sparse signal reconstruction, this paper proposes a smooth norm optimization algorithm,which is different from the minimum 1 norm optimization algorithm. This paper mainly studies the choice of important parameters in this signal reconstruction algorithm. Taking the handwritten digital image hbraly of the United States Postal Service（USPS） as test samples, we make one-dimensional signal reconstruction and two-dimensional image reconstruction experiments. The experimental results show the advantage of the norm algorithm in image reconstruction precision and reconstruction time, which lays the theoretical foundation for subsequent research on image engineering.
出处
《成都大学学报（自然科学版）》
2014年第2期141-144,共4页
Journal of Chengdu University（Natural Science Edition）
关键词
压缩感知
图像重建
稀疏信号重建
e^0范数优化
compressed sensing
image reconstruction
sparse signal reconstruction
eo norm optimization
