玉米近红外光谱在仿生模式识别中的特征提取方法研究  

Study of Feature Extraction Methods for Maize's Near Infrared Spectra in Biomimetic Pattern Recognition

作　　者：沈立峰[1] 贾仕强[1] 郭婷婷[2] 邬文锦[1] 严衍禄[1] 安冬[1] 

机构地区：[1]中国农业大学信息与电气工程学院,北京100083 [2]中国农业大学国家玉米改良中心,北京100193

出　　处：《光谱学与光谱分析》2012年第4期939-943,共5页Spectroscopy and Spectral Analysis

基　　金：中央高校基金科研业务费专项项目(2010JS097);国家自然科学基金项目(60805011);高等学校博士学科点专项科研基金项目(200800191028)资助

摘　　要：近红外光谱特征提取是近红外光谱定性分析的关键步骤,其质量直接影响定性分析结果。采用漫透射方法测量8个玉米品种的近红外光谱,经预处理后,分别采用PCA,ICA,PLS-DA和小波分解四种方法对光谱进行特征提取,并使用仿生模式识别方法建立了8个玉米品种识别模型,最后使用测试集数据进行模型测试。结论如下:使用PLS-DA方法进行特征提取后建立的模型正确识别率优于使用PCA,ICA和小波分解特征提取后建立的模型。Near infrared spectrum is an important step in near infrared spectrum qualitative analysis, which influences the qualitative analysis results directly. Diffuse transmittance measurements mode was used to collect spectral data of eight maize varieties. PCA, ICA, PLS-DA and wavelet transformation were used to extract features of pretreated data. Finally, we used the test set data to test the recognition models of eight maize varieties which were built based on biomimetic pattern recognition （BPR）. We draw a conclusion that PLS-DA can make models get higher average correct recognition rate than PCA, ICA and Wavelet transformation.

关 键 词：玉米品种 近红外光谱 仿生模式识别 特征提取 漫透射 

分 类 号：O657.3[理学—分析化学] S123[理学—化学]