高光谱图像法对稻谷贮藏中五种常见真菌生长拟合及区分  

Growth simulation and discrimination of five fungi from rice storage using hyperspectral reflectance imaging technique

作　　者：肖慧[1] 王振杰[1] 孙晔[1] 顾欣哲 屠康[1] 都立辉[2] 潘磊庆[1] 

机构地区：[1]南京农业大学食品科技学院,江苏南京210095 [2]南京财经大学食品科学与工程学院,江苏南京210023

出　　处：《食品工业科技》2016年第13期276-281,共6页Science and Technology of Food Industry

基　　金：粮食公益性行业科研专项经费资助项目(201313002-01);国家科技支撑项目(2015BAD19B03);中央高校基本科研业务费专项(KYLH201504);国家自然科学基金项目(31101282)

摘　　要：利用高光谱成像系统（HIS）获取稻谷贮藏中常见真菌（黑曲霉、米曲霉、杂色曲霉、构巢曲霉、桔青霉）在马铃薯葡萄糖琼脂板上培养期间的高光谱图像,波峰709 nm处的光谱值和全波段光谱值的第一主成分得分两种方法构建真菌Gompertz函数的生长模拟模型。Gompertz函数拟合结果显示,五种真菌基于全波段光谱值PCA分析后的第一主成分得分建立的生长拟合模型R2为0.1781~0.9501,基于波峰709 nm光谱值建立的拟合模型R2为0.9095~0.9679,效果明显优于第一主成分得分的建模效果。另外,主成分分析（PCA）结合偏最小二乘法判别分析（PLS-DA）可以区分五种不同菌种。其中,训练集和测试集中,PLS-DA模型对培养48 h的黑曲霉、米曲霉、构巢曲霉、桔青霉四种真菌及对照组的区分准确率为100%;而对杂色曲霉,训练集区分准确率为100%,测试集的区分率为33.33%。结果表明高光谱图像技术能够用来对真菌种类进行区分。Hyperspectral imaging system （HIS）was used in this study to acquire the spectral responses of fungi （ Asp. Niger, Asp. Oryzae, Asp. Versicolor, Asp. Nidulans, P. Citrinum） inoculated on potato dextrose agar plates. Two methods for calculating HIS parameters,including the spectral response values of the wave peak at 709 nm, and the scores of the first principal component of the whole spectral range（400-]000 nm）using principal component analysis（PCA）, were used to simulate the growth of fungi. The results of Gompertz model revealed that the coefficients of determination（/：？2）of five fungi based on the score of the first principal component were 0.1781- 0.9501 ,while R2 with 0.9095-0.9679 based on the spectral response value of the wave peak at ＂709 nm showed better aptitude than the previous method.In addition,fungi species can be discriminated by PCA and partial least squares discrimination analysis （PLSDA） using the spectral information of the full wavelength range. All the classification accuracy of the test group and training group sets by PLSDA models for four fungi（Asp.Niger,Asp. Oryzae,Asp. Nidulans, P.Citrinum）cultured for 48 h were 100% ,with the exception of 33.33% for the classification accuracy of training group of Asp. Versicolor.This paper supplied a new technique and useful information for further study into detecting rice spoilage caused by fungi based on HIS.

关 键 词：高光谱图像 稻谷 真菌 生长拟合 区分 

分 类 号：TS255.4[轻工技术与工程—农产品加工及贮藏工程]