近红外玉米品种鉴别系统预处理和波长选择方法  

Effects of Spectral Pretreatment and Wavelength Selection on Discrimination of Maize Seed Varieties by NIR Spectroscopy

作　　者：郭婷婷[1] 邬文锦[2] 苏谦[2] 王守觉[1] 安冬[2] 

机构地区：[1]中国科学院半导体研究所,北京100083 [2]中国农业大学信息与电气工程学院,北京100083

出　　处：《农业机械学报》2009年第S1期87-92,共6页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金资助项目(60805011;60753001);高等学校博士学科点专项科研基金资助项目(200800191028)

摘　　要：以7个品种玉米籽粒的鉴别系统为研究对象,对比研究了6种预处理方法和波长选择对模型鉴别能力的影响。结果表明,在被比较的6种预处理方法中,一阶导数方法能够使模型有更好的鉴别性能。使用一阶导数预处理和全光谱区的模型平均正确识别率和正确拒识率最高,分别为98.6%和98%,有5个品种的模型的正确识别率和正确拒识率都达到了100%。波长选择对一阶导数模型没有明显作用,但能使标准正态变量变换和矢量归一化模型鉴别准确度得到较大提高。In this paper,we study the effects of wavelength selection and data pretreatments,including no pretreatment,standard normal variate transformation(SNV),vector normalization,smoothing,first and second derivative transformation,on the discrimination of maize seed varieties.The performance of the pretreatment methods is evaluated on the basis of the two data sets: all-range spectral data and the data of the characteristic wavelengths selected by a standard deviation-based feature selection method,respectively.The correct acceptance rate(CAR) and the correct rejection rate(CRR) are used as the criteria for the discrimination models.The results show that the best model uses first derivative and all-range spectral and using the best model both CAR and CRR for five varieties reach 100%,and the average CAR and CRR attains 98.6% and 98%.The wavelength selection can only improve CGR of SNV and vector normalization models.

关 键 词：近红外光谱 玉米 品种鉴别 预处理 波长选择 

分 类 号：S513[农业科学—作物学]