频域二元纯相位编码压缩成像  

Binary Pure Phase Encoding Compressive Imaging in Frequency Domain

作　　者：张成[1] 张芬[1,2] 沈川[1] 章权兵[1] 韦穗[1] 王岳[1] 

机构地区：[1]计算智能与信号处理教育部重点实验室(安徽大学),合肥230039 [2]安徽省现代成像与显示技术重点实验室,合肥230039

出　　处：《计算机研究与发展》2014年第9期2070-2080,共11页Journal of Computer Research and Development

基　　金：NSFC-广东联合基金项目(U1201255);国家自然科学基金项目(61201396;61201227;61301296;61377006);高等学校博士学科点专项科研基金项目(20113401130001);安徽省自然科学基金项目(1208085QF114);安徽大学博士科研启动经费项目(33190218);安徽大学青年基金项目(KJQN1120)

摘　　要：超分辨率被认为是光学成像和图像处理的"圣杯"之一.压缩感知理论的引入给出一种新的实现从单幅低分辨率图像的超分辨率重构方法,避免了传统超分辨率方法需要多幅亚像素图像的弊端.在分析压缩感知测量矩阵与光学成像系统之间对应约束异同的基础上,提出一种基于4-f光学架构的频域二元相位编码压缩成像方法,可以实现在单次曝光条件下获得的单幅低分辨率测量图像中实现超分辨率重建,不需要其他任何额外的信息采集.二元相位掩膜比均匀相位掩膜更容易物理实现,是压缩成像物理实现的一种更加可行的方案.模拟实验表明提出的方法可以有效地捕获图像的信息与高精度重建.此外,对于大尺度图像重建,该方法在重建时间方面优于Romberg提出的随机解调方法,在更符合实际方面的采样策略方面优于Yin提出的RecPC方法.Super resolution（SR）is considered as one of the＂holy grails＂of optical imaging and image processing.The introduction of compressive sensing theory presents a novel super-resolution reconstruction method from a single low-resolution image,which can avoid the requirements for the multiple sub-pixel images of traditional superresolution method.Analyzing the requirements of the similarities and differences between compressed sensing measurement matrices and optical imaging systems,a binary phase encoding compressive imaging method based on the 4-f optical architecture is presented,with the phase in the frequency domain randomly modulated,which can achieve superresolution reconstruction from single low-resolution measurement images obtained with single exposure conditions,no other additional information collected.Binary phase mask is much easier to implement than random phase mask with uniform distribution,which is a more viable scheme for physical realization of compressive imaging.Simulation experiments demonstrate that the proposed method can effectively capture compressive measurements and implement super-resolution reconstruction in a single shot condition.Furthermore,another experiments show that this method is also more applicable to large-scale image reconstruction compared with random demodulation（RD）proposed by Romberg in the reconstruction time,and more practical in the sampling scheme than RecPC method proposed by Yin.

关 键 词：压缩成像 图像超分辨率 随机相位编码 二元相位编码 4-f光学架构 

分 类 号：TP334.22[自动化与计算机技术—计算机系统结构]