LINEAR-QUADRATIC NOISE-SMOOTHING FILTERS FOR QUANTUM-LIMITED IMAGES

被引：6

作者：

CHAN, CL ^{[1
]}

KATSAGGELOS, AR ^{[1
]}

SAHAKIAN, AV ^{[1
]}

机构：

[1] NORTHWESTERN UNIV, MCCORMICK SCH ENGN & APPL SCI, DEPT ELECT ENGN & COMP SCI, EVANSTON, IL 60208 USA

来源：

IEEE TRANSACTIONS ON IMAGE PROCESSING | 1995年 / 4卷 / 09期

关键词：

Number:; -; Acronym:; Sponsor: Siemens Foundation;

D O I：

10.1109/83.413179

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this correspondence, we consider the use of nonlinear estimators for the noise smoothing of images obtained under quantum-limited imaging conditions. A Volterra expansion is investigated from which a set of linear quadratic filters is derived using higher order statistics. The filters are applicable for single frame and multiple frames of a single scene imaged under low-light levels.

引用

页码：1328 / 1333

页数：6

共 16 条

[1]

[Anonymous], 1983, MED IMAGING SYSTEMS

[2] Recursive locally linear MMSE motion-compensated image sequence filtering under quantum-limited conditions [J].