漫反射和透射光谱检测马铃薯黑心病的比较

针对马铃薯黑心病不易检测,提出马铃薯黑心病的光学无损检测方法,并比较了马铃薯黑心病的漫反射光谱和透射光谱检测方法。通过高光谱图像采集系统、透射光谱采集系统和傅里叶变换近红外光谱仪获取合格马铃薯与黑心病马铃薯的可见/近红外漫反射光谱、可见/近红外透射光谱以及近红外漫反射光谱,并采用偏最小二乘-线性判别分析方法建立马铃薯黑心病的识别模型。透射光谱采集系统采集的可见/近红外透射光谱所建模型的判别正确率最高,对测试集样本的识别正确率为98.46%;高光谱图像采集系统获取的可见/近红外漫反射光谱经二阶导与标准化组合预处理后所建模型对测试集样本的识别正确率为92.31%;傅里叶变换近红外光谱仪获取的漫反射光谱经标准正态变量变换与标准化组合预处理后所建模型对测试集样本的识别正确率90.77%。试验结果表明:采用光谱检测马铃薯黑心病,透射光谱系统优于高光谱成像系统,高光谱成像系统优于傅里叶近红外光谱仪。研究结果为马铃薯内部缺陷的光谱定性判别及便携式仪器的研制提供了参考。     

基于近红外光谱和机器视觉融合技术的板栗缺陷检测

为提高合格和缺陷板栗分级检测识别精度,提出了近红外光谱和机器视觉的多源信息融合技术的板栗缺陷检测方法。试验以湖北京山板栗为试验对象,利用BP神经网络方法建立了基于近红外光谱、机器视觉和多源信息融合技术的板栗分级检测模型。试验结果表明,3种识别模型对对训练集板栗回判率分别为96.25%、96.67%和97.92%;对测试集板栗的识别率为86.25%、83.75%和90.00%。基于近红外光谱和机器视觉的多源信息融合技术进行板栗分级检测的方法是可行的,融合模型较单独采用机器视觉技术或近红外光谱分析技术建立模型的识别率均有显著提高。     

椪柑果实病虫害的傅里叶频谱重分形图像识别

为探讨植物病虫害互不交叉、重叠的数字典型特征值来进行病虫害计算机识别,研究了椪柑病虫害为害状图像傅里叶变换幅度谱的多重分形特征。首先,用改进型分水岭算法检测病虫害为害状边缘,并对其进行区域合并,形成病虫害为害状边界。其次,对病虫害果进行二维离散傅里叶变换,依据病虫害为害状边界进行图像标记,提取标记区域内的傅里叶变换幅度谱图。最后,对傅里叶变换幅度谱图进行多重分形分析及多重分形谱的二次拟合,将拟合抛物线段的高度、宽度和质心坐标作为病虫害特征值,并以此为输入变量,建立 BP 神经网络椪柑病虫害识别模型来进行病虫害识别,椪柑蓟马、花潜金龟子、吸果夜蛾、侧多食跗线螨、椪柑炭疽病5类病虫害30组测试样本中吸果夜蛾识别正确率最高96.67%,侧多食跗线螨识别正确率最低86.67%,平均正确识别率为92.67%。试验结果表明：傅里叶变换幅度谱图的多重分形谱高度、宽度和质心坐标较精确地刻画了病虫害为害状这类复杂生物体的特征,该方法可进行椪柑病虫害自动识别,并可推广到其他植物的病虫害机器识别中。     

分提橄榄油中主要脂肪酸成分傅里叶变换红外光谱法测量（英）

为了测量从橄榄油中分提的高、低熔点油脂的脂肪酸成分,在4 000～600 cm-1 的范围测量了31个含有不同脂肪酸成分植物油的傅里叶变换红外光谱,用于建立偏最小二乘（PLS）回归分析校正模型。在油脂的傅里叶变换红外光谱变量和脂肪酸组成变量之间建立了交叉验证的PLS校正模型。为了校正油酸和亚油酸含量,在4?000～600 cm-1 的频率范围,经平滑,二阶导数,规范化处理的红外光谱获得了最好的交叉验证校正模型和最佳的预测结果。PLS校正模型预测结果表明,与高熔点橄榄油（油酸,72.29%,亚油酸,9.98%）相比,低熔点橄榄油含有较高的油酸含量和亚油酸含量（油酸,77.46%,亚油酸,12.51%）,预测的结果与气相色谱测量的结果有很好的一致性。建立的PLS校正模型预测橄榄油的不饱和脂肪酸含量具有较好的相关性。该研究为分提油脂质量的判别评价提供了便捷的方法。     

两种稻谷胶稠度测定方法的比较分析

为探索快速准确检测稻谷胶稠度的方法,本研究通过近红外漫反射红外光谱技术(NIRDRS)和傅里叶变换中红外漫反射红外光谱技术(FTIRDRS)结合偏最小二乘法(PLS),分别建立107个稻谷样品的胶稠度快速测定红外模型,而后利用区间偏最小二乘法(iPLS)及反向区间偏最小二乘法(BiPLS)对模型进行优化,得到较优的胶稠度测定分析通用模型。结果表明,DRIFTS原始光谱经7点平滑预处理和BiPLS优化,得到最佳模型的交互验证系数(R²)、交叉验证均方差(RMSECV)、预测均方差(RMSEP)及相对分析误差(RPD)分别为0.965 81、4.79、4.73及2.66。最佳近红外漫反射光谱模型是经多元散射校正(MSC)预处理、BiPLS优化后建立的,其R²、RMSECV、RMSEP及RPD分别为 0.964 58、4.35、3.68及3.42。10组外部验证性试验中NIRDRS模型的平均相对误差为1.93%,FTIRDRS模型的平均相对误差为2.60%,表明两种方法均对稻谷胶稠度含量有较强的预测能力和良好的预测效果,均有替代传统国标法测定稻谷胶稠度的潜力。     

玉米种子活力近红外光谱智能检测方法研究

为了实现玉米种子活力的快速无损检测,提出利用近红外光谱和BP神经网络来建立玉米种子活力智能检测模型。首先通过人工老化将样本按老化程度分为3种级别,采集样本的近红外光谱。分别通过卷积平滑(S-G)和多元散射校正(MSC)及二者组合的方法消除光谱噪声和去除奇异光谱。然后分别用主成分分析(PCA)和离散多带小波变换(DWT)提取光谱特征,作为BP神经网络的输入。依据预处理及特征提取的不同构建出6种BP神经网络种子活力检测模型。试验结果表明,组合预处理方法与主成分分析特征提取结合构建的模型最优,其识别的准确率为95.0%,平均识别时间为26.25ms。研究结果为玉米种子活力的快速无损检测提供了理论依据和实用方法。     

基于近红外光谱的板栗水分检测方法

含水率是影响板栗贮藏、加工的关键指标之一,该文应用近红外光谱技术对板栗含水率进行快速无损检测。试验对240个板栗样本的带壳光谱和栗仁板栗光谱采用SPXY算法进行样本集划分,利用偏最小二乘法建立含水率定量检测模型,并对微分、多元散射校正、变量标准化等多种预处理方法对建模结果的影响进行比较。结果表明：栗仁和带壳板栗的光谱经一阶微分预处理后所建模型性能最佳,其中栗仁的水分检测模型校正集和验证集的相关系数分别为0.9359和0.8473,校正均方根误差为1.44%,验证均方根误差为1.83%;带壳板栗光谱所建模型校正集和验证集的相关系数分别为0.8270和0.7655,校正均方根误差为2.27%,验证均方根误差为2.35%。受栗壳的影响,带壳板栗光谱模型对含水率的预测精度低于栗仁光谱模型的预测精度。研究表明,近红外光谱分析技术可用于板栗含水率的快速无损检测。     

法布里干涉、傅里叶变换近红外光谱仪采集西湖龙井茶近红外光谱的比较

本文介绍了基于法布里干涉的便携近红外光谱仪的仪器性能和干涉原理,并且以西湖龙井茶为例,与傅里叶变换型近红外光谱仪所采集的近红外光谱进行了比较.结果表明,两种仪器采集的光谱数据之间的相关系数(r)可以达到0.992 7,一阶导数谱数据间的相关系数可达到0.981 5.基于法布里干涉的便携近红外光谱仪在性能方面可以与傅里叶变换近红外光谱仪相媲美.然而,便携近红外光谱仪在农产品品质分析方面更广泛地应用还需要进一步研究.     

支持向量机在苹果分类的近红外光谱模型中的应用

建立了一套苹果近红外光谱采集装置来减少因苹果的部位差异性而造成的试验误差。采用一种新的机器学习算法——支持向量机(SVM)建立不同产地、不同品种苹果的近红外光谱分类模型。通过选定RBF函数作为核函数，并确定合适的光谱预处理方法和核函数中惩罚系数C、正则化系数γ，使得所建立的不同品种苹果分类模型的回判识别率和预测识别率均达到100%，不同产地苹果分类模型的回判识别率为87%，预测识别率为100%，与传统的判别分析法相比其预测识别精度提高5%左右。结果表明，支持向量机可以建立高精度的苹果近红外光谱分类模型。     

霉变稻谷脂肪酸含量的光谱检测模型构建与优化分析

为了实现霉变稻谷脂肪酸含量无损、快速检测,该文研究应用可见/近红外光谱技术检测霉变稻谷的脂肪酸含量。考虑到直接选用霉变稻谷可见/近红外光谱数据构建脂肪酸含量预测模型存在建模费时、预测失准等问题,研究提出了霉变稻谷脂肪酸含量的可见/近红外优化校正模型。研究中通过光谱-理化值共生距离(sample set partitioning based on joint xy distance,SPXY)算法结合偏最小二乘法初步分析了不同校正集样本预测霉变稻谷脂肪酸含量的差异;利用连续投影算法(SPA)提取了反映霉变稻谷脂肪酸含量变化的特征波段;采用偏最小二乘法(partial least square,PLS)和多元线性回归法(multivariable linear regression,MLR)分别建立了基于特征波段光谱反射值的霉变稻谷脂肪酸含量预测模型,并对比分析了采用SPXY样本集划分的模型预测效果。结果表明:采用SPXY法筛选出的65个校正集样本分布与初始校正集相近,脂肪酸含量变化范围为18.55~127.26 mg,其标准差为32.39;SPA算法最终从256个全光谱波段中优选出9个特征波段,实现了光谱数据的压缩;分别建立的SPXY-SPA-PLSR模型和SPXY-SPA-MLR模型预测霉变稻谷脂肪酸含量相关系数RP为0.922 1和0.915 9,预测均方根误差RMSEP为13.889 3和14.261 0;SPXY筛选校正集所构建模型预测精度与初始校正集所建模型相当,但校正集样本数量减少为初始校正集的41%,运算时长缩短为初始样本集的32%,提高了模型的校正速度。     

A Comparative Study of Fourier Transform Raman and NIR Spectroscopic Methods for Assessment of Protein and Apparent Amylose in Rice

Fourier‐transform Raman (FT‐Raman) spectroscopy and near‐infrared (NIR) reflectance spectroscopy were used to compare calibration models for determining rice cooking quality parameters such as apparent amylose and protein. Samples from two seasons were used in each calibration set. The laboratory values ranged from 4.89 to 12.48% for protein and from 0.2 to 25.7% for amylose. The data for both FT‐Raman and NIR were preprocessed with orthogonal signal correction (OSC) for standardization. For both spectroscopic methods, five models were optimized by partial least squares regression (PLSR) and by Martens' uncertainty regression (MUR), including no processing, smoothing, normalization, first derivative (D1), and second derivative (D2). Based solely on standard error of cross‐validation (SECV), the FT‐Raman method was superior to the NIR method for protein. For amylose, the FT‐Raman and NIR methods resulted in similar calibration statistics with a high precision, with the FT‐Raman requiring fewer factors. The best FT‐Raman models were generated from OSC preprocessing with MUR for protein (SECV 0.15%, five factors) and from OSC without MUR for amylose (SECV 0.70%, seven factors). The best NIR models were obtained with D2 transform of OSC spectra for protein (SECV 0.22%, four factors) and with OSC spectra for amylose (SECV 0.57%, 11 factors).     

近红外光谱结合SIMCA法溯源羊肉产地的初步研究

产地溯源是食品安全追溯制度的重要组成部分。该文采用近红外光谱结合簇类独立软模式法(SIMCA)建立了羊肉产地溯源模型。结果表明,在11995～3999cm-1波长范围内,光谱经5点平滑(Smooth)与多元散射校正(MSC)预处理,山东济宁市、河北大厂县、内蒙临河市、宁夏银川市4个产地模型的主成分数分别为5、6、5、6时,采用SIMCA模式识别方法可以建立稳健的羊肉产地溯源模型;在1%的显著水平下,4个产地校正集模型对未知样本的识别率分别为95%、100%、100%、100%,拒绝率均为100%;其验证集模型的识别率分别为100%、83%、100%、92%,拒绝率均为100%。该研究表明,近红外光谱技术作为一种羊肉产地的溯源方法切实可行。     

基于相关系数法与遗传算法的啤酒酒精度近红外光谱分析

以啤酒的酒精度的快速检测为研究对象,针对采用偏最小二乘(Partial Least Squares,PLS)法建立近红外光谱预测模型时波长筛选问题,提出将相关系数法与遗传算法(Genetic Algorithms,GA)相结合提取光谱有效信息,提高预测模型的精度的方法。结果表明：该方法应用于啤酒酒精度近红外光谱检测中,吸收光谱和一阶导数光谱的预测建模的波长个数分别减少了83%、82%,预测平均相对误差分别降低了0.42%、0.64%,不仅简化、优化了模型,而且增强了预测建模型的预测能力,是一种采用PLS法建立预测模型前行之有效的降低和优选波长的方法。     

Authentication of the botanical origin of honey by near-infrared spectroscopy

Fourier transform near-infrared spectroscopy (FT-NIR) was evaluated for the authentication of eight unifloral and polyfloral honey types (n = 364 samples) previously classified using traditional methods such as chemical, pollen, and sensory analysis. Chemometric evaluation of the spectra was carried out by applying principal component analysis and linear discriminant analysis. The corresponding error rates were calculated according to Bayes' theorem. NIR spectroscopy enabled a reliable discrimination of acacia, chestnut, and fir honeydew honey from the other unifloral and polyfloral honey types studied. The error rates ranged from <0.1 to 6.3% depending on the honey type. NIR proved also to be useful for the classification of blossom and honeydew honeys. The results demonstrate that near-infrared spectrometry is a valuable, rapid, and nondestructive tool for the authentication of the above-mentioned honeys, but not for all varieties studied.     

Improved analysis and modelling of soil diffuse reflectance spectra using wavelets

Diffuse reflectance spectroscopy using visible (vis), near‐infrared (NIR) and mid‐infrared (mid‐IR) energy can be a powerful tool to assess and monitor soil quality and function. Mathematical pre‐processing techniques and multivariate calibrations are commonly used to develop spectroscopic models to predict soil properties. These models contain many predictor variables that are collinear and redundant by nature. Partial least squares regression (PLSR) is often used for their analysis. Wavelets can be used to smooth signals and to reduce large data sets to parsimonious representations for more efficient data storage, computation and transmission. Our aim was to investigate their potential for the analyses of soil diffuse reflectance spectra. Specifically we wished to: (i) show how wavelets can be used to represent the multi‐scale nature of soil diffuse reflectance spectra, (ii) produce parsimonious representations of the spectra using selected wavelet coefficients and (iii) improve the regression analysis for prediction of soil organic carbon (SOC) and clay content. We decomposed soil vis‐NIR and mid‐IR spectra using the discrete wavelet transform (DWT) using a Daubechies’s wavelet with two vanishing moments. A multiresolution analysis (MRA) revealed their multi‐scale nature. The MRA identified local features in the spectra that contain information on soil composition. We illustrated a technique for the selection of wavelet coefficients, which were used to produce parsimonious multivariate calibrations for SOC and clay content. Both vis‐NIR and mid‐IR data were reduced to less than 7% of their original size. The selected coefficients were also back‐transformed. Multivariate calibrations were performed by PLSR, multiple linear regression (MLR) and MLR with quadratic polynomials (MLR‐QP) using the spectra, all wavelet coefficients, the selected coefficients and their back transformations. Calibrations by MLR‐QP using the selected wavelet coefficients produced the best predictions of SOC and clay content. MLR‐QP accounted for any nonlinearity in the data. Transforming soil spectra into the wavelet domain and producing a smaller representation of the data improved the efficiency of the calibrations. The models were computed with reduced, parsimonious data sets using simpler regressions.     

Rapid Variety Identification of Pure Rough Rice by Fourier‐Transform Near‐Infrared Spectroscopy

Rice variety is considered as an important factor influencing cooking and processing quality because of variations in size, shape, and constitution. Difficulty in management of rough rice with lower varietal purity becomes a significant problem in rice production and can result in the reduction of rice quality. Fourier‐transform near‐infrared (FT‐NIR) spectroscopy was used to identify the variety of rough rice through whole‐grain techniques. Moist rough rice samples (n = 259) comprising five varieties (Khao Dawk Mali 105 [KDML105], Pathum Thani 1, Suphan Buri 60, Chainat 1, and Pitsanulok 2) were gathered from different locations around Thailand and scanned in the NIR region of 9088–4000 cm^–1 in reflectance mode. Soft independent modeling of class analogies (SIMCA) and partial least squares discriminant analysis (PLSDA) methods were used for identification by utilizing preprocessed spectra. The highest identification accuracy achieved was 74.42% by the SIMCA model and 99.22% by the PLSDA model. The best PLSDA model demonstrated approximately 97% correct identification for KDML105 samples and 100% for the others. This study raises the possibility of applying FT‐NIR spectroscopy as a nondestructive technique for rapidly identifying moist rough rice varieties in routine quality assurance testing.     

基于漫反射光谱的初制绿茶含水率无损检测方法

茶叶含水率是影响茶叶加工品质的一项重要指标。为了实现茶叶加工中含水率的快速检测,该文提出了一种应用漫反射光谱技术的绿茶初制过程中含水率无损检测方法。采用波长范围在325～1 075 nm 的可见-短波近红外光谱仪,对炒青绿茶在8个加工工序中随机抽取的568个茶叶样本进行漫反射光谱扫描,光谱扫描后立即测量样本的含水率。对于得到的光谱数据,采用小波变换降低其信息维度并提取小波系数,比较小波低频系数对于光谱特征信息的提取能力,结果显示,小波低频系数能够有效提取原始光谱数据中的特征信息。采用3种回归算法：偏最小二乘回归、神经网络和支持向量机分别建立含水率的测量模型。比较发现支持向量机回归模型的结果最优,建模相关系数为0.9985,预测相关系数为0.9875。研究结果表明,漫反射光谱可以用于绿茶含水率的无损、快速检测,小波变换是一种有效的光谱特征提取算法,而且支持向量机回归算法具有高精度和强泛化能力,可广泛用于回归分析。     

Spectroscopic evaluation of the surface quality of apple

Different spectroscopic techniques based on infrared and Raman were used to evaluate the natural wax and related surface quality of apple fruit. Transmission near-infrared (NIR) spectroscopy was applied to solutions of single wax components and extracted apple wax. Fourier transform infrared (FTIR) spectroscopy was used for transmission measurements of wax films on NaCl crystals, diffuse reflectance spectroscopy (DRIFTS) was used to analyze wax powders, and FT-Raman spectroscopy was explored to examine intact wax layers on whole fruit. The natural wax layers of apple fruit from a maximum of three different cultivars (Jonagold, Jonagored, and Elshof) from three picking dates (early, commercial, and late), three controlled atmosphere storage durations (0, 4, and 8 months), and three shelf life periods (0, 1, and 2 weeks) within each storage duration were examined. Canonical discriminant analysis was carried out on the first derivative NIR and FTIR spectra to describe the information contained in the spectra. Discrimination between cultivars and between storage duration based on wax layer properties was achieved with reasonable accuracy from both of the techniques. Information contained in the spectra of apples from different picking dates and shelf life periods was not significant. Differences between cultivars and storage periods in this analysis mostly related to differences in the number of aliphatic chains (e.g., alkanes and esters) and the presence of alpha-farnesene. No satisfactory results were obtained by means of Raman spectroscopy and DRIFTS.     

基于近红外光谱技术的淡水鱼品种快速鉴别

为探索淡水鱼品种的快速鉴别方法,该文应用近红外光谱分析技术,结合化学计量学方法,对7种淡水鱼品种的判别分类进行了研究。采集了青、草、鲢、鳙、鲤、鲫、鲂等7种淡水鱼,共665个鱼肉样品的近红外光谱数据,经过多元散射校正(multiplicative scatter correction,MSC)、正交信号校正(orthogonal signal correction,OSC)、数据标准化(standardization,S)等20种方法预处理,在1 000~1 799 nm范围内分别采用偏最小二乘法(partial least square,PLS)、主成分分析(principal component analysis,PCA)和BP人工神经网络技术(back propagation artificial neural network,BP-ANN)、偏最小二乘法和BP人工神经网络技术对7种淡水鱼原始光谱数据进行了鉴别分析。结果表明,近红外光谱数据,结合主成分分析和BP人工神经网络技术建立的淡水鱼品种鉴别模型最优,模型的鉴别准确率达96.4%,对未知样本的鉴别准确率达95.5%。模型具有较好的鉴别能力,采用该方法能较为准确、快速地鉴别出淡水鱼的品种。     

羊肉色泽傅立叶变换近红外光谱定量分析方法研究

以从北京市、山西大同市、宁夏吴忠市3个地区筛选的有代表性的227份羊肉样品为试材,应用傅里叶变换近红外光谱技术探讨羊肉色泽无损检测的方法。以决定系数(R2)、校正标准差(RMSECV)和预测标准差(RMSEP)为近红外光谱检测模型的评价指标,采用偏最小二乘法(PLS)对近红外光谱信息与样品的色差e值进行拟合,确定最佳的光谱预处理方法、主成分数和光谱区间范围。结果表明:所选227个羊肉样品的色差e值分布范围为1.556～9.879,其中80%以上的样品e值在1～5之间,具有显著的代表性;在11995.5～4597.6cm-1的波段范围内,最佳主成分数为6时,近红外光谱经最大最小归一法处理后,建立的羊肉色泽预测模型精度最高,R2达到0.776,RMSECV为0.451;用此模型对预测集48个样品进行预测,预测值与实测值的相关系数(R)为0.835,RMSEP为0.517,该研究表明利用近红外光谱技术检测羊肉色泽可行。