摘要
提高超分辨率图像重建效果一个重要因素是减小数据"异常点"的影响。介绍了LMS算法在超分辨率图像重建中的应用,在这种算法的静态模型基础上,提出了一种重建视频图像序列过程中消除"异常点"影响的方法。在考虑配准误差的条件下,这种方法可以适用于实际应用中的瞬态和稳态相位的图像。
Improving super-resolution reconstruction of video image sequences effect is highly dependent on reducing the influ- ence of the data outliers.This work addresses the design of the Least Mean Square (LMS) algorithm applied to super-resolution reconstruction.Based on a statistical model of the algorithm behavior,the authors propose a design strategy to annihilate the effects of outliers on the reconstructed image sequence.The authors show that the proposed strategy can improve the performance of the algorithm in both transient and steady-state phases of adaptation in practical situations when registration errors are considered.
出处
《计算机工程与应用》
CSCD
北大核心
2008年第19期187-189,共3页
Computer Engineering and Applications
基金
国家自然科学基金(the National Natural Science Foundation of China under Grant No.60641010)
关键词
超分辨率
视频图像序列
图像重建
LMS
异常点
步长
super-resolution
video image sequences
image restoration
Least Mean Square(LMS)
outlier
step-size