正交信号校正算法及其在光谱处理中的应用

The algorithms of orthogonal signal correctionand its application in spectra processing

基于正交投影的正交信号校正(OSC)算法是近年来在光谱处理上很活跃的一种方法。本文介绍了OSC算法的基本原理,并对S.Wold、Fearn等人的比较成熟的5种正交信号校正算法作了比较详细的介绍。利用谷物的近红外数据,采用5种不同的OSC算法对谷物中的湿度、油含量、蛋白质和淀粉含量的预报情况进行了比较,并讨论了OSC组分数对预处理结果的影响。结果表明,各种正交信号校正算法基本上都能取得比单纯使用PLS更好的结果。

<Abstrcat>The orthogonal signal correction (OSC) is a popular algorithm in the signal preprocess. This paper presents the basic principle of OSC and a comparison on the algorithms proposed by S.Wold, Fearn, etc. The corn NIR data has been used to evaluate the OSC algorithms. The contents of humidity, oil, protein and starch in the corn are gained by using OSC. The variance of preprocessing results with OSC components numbers has also been discussed. The experiment results show that better performance can be achieved with the OSC algorithm than PLS.