苹果质地的近红外光谱无损检测模型研究

为了建立快速而无损检测苹果质地的新方法,应用近红外光谱仪研究不同建模方法和光谱预处理方法对苹果质地(脆度、硬度、回复性、凝聚性和咀嚼性)无损检测模型性能的影响。结果表明,波长范围400~2500nm内,采用改进偏最小二乘法、原始光谱结合反相多元离散校正处理所建苹果质地的校正模型最优,脆度、硬度、回复性、凝聚性和咀嚼性预测相关系数均大于0.8,而预测标准误差分别为7.6763N、6.5876N、0.0085、0.0175、1.2466N,残差之和均小于0.2。因此,通过近红外光谱对苹果质地进行快速而无损检测具有一定可行性,但模型精度有待进一步提高。     

基于高光谱技术的羊肉含水率无损检测

利用高光谱成像系统(1000~2500 nm)对羊肉含水率进行无损检测研究。对108个羊肉样本进行光谱信息采集,通过标准正态变换法、归一化法、去趋势校正法、S-G卷积平滑法、导数法、多元散射校正法对原始光谱进行预处理,对全波段下的原始光谱和预处理后的光谱建立偏最小二乘回归(PLSR)模型,优选出的最佳预处理算法为去趋势校正法。原始数据经去趋势校正法预处理后,采用相关系数法选取特征波长,建立特征波长下羊肉含水率的 PLSR模型和逐步多元线性回归(SMLR)模型。结果表明,SMLR模型对含水率预测效果最好,校正集相关系数R_c为0.8597,标准误差SEC为0.0521;预测集相关系数R_p为0.8654,标准误差SEP为0.0387。研究表明,利用高光谱成像技术检测羊肉含水率是可行的。     

基于高光谱成像技术无损检测苹果表面缺陷

基于高光谱成像技术结合模式识别,建立了苹果表面缺陷识别模型。首先,利用高光谱图像采集系统采集完好无损和表面有缺陷苹果的高光谱图像,提取感兴趣区域的平均光谱反射率;然后,比较标准正态变换(SNV)和多元散射校正(MSC) 2种光谱预处理方法对建模效果的影响,得出MSC为建模最优预处理方法。最后,采用主成分分析法选择累计贡献率超过99%的前5个主成分作为样本集特征光谱数据,分别建立了基于K最近邻(KNN)模式识别和偏最小二乘判别分析(PLS-DA)识别模型。结果表明:光谱经MSC预处理后,基于PLS-DA建立的识别模型对校正集和检验集识别率均达到100%,表明基于高光谱成像技术结合模式识别可实现苹果表面缺陷的无损检测。     

䥺Symbol`@@基于近红外光谱漫透射技术的苹果可溶性固形物含量在线检测

为研究苹果的内部品质,提高检测的速度和稳定性,将近红外光谱漫透射技术应用于在线检测研究,并采取偏最小二乘回归(PLSR)算法结合不同光谱预处理方法建立苹果内部的可溶性固形物含量(SSC)的定量模型。结果表明:采用一阶微分结合多元散射校正(MSC)预处理后的模型最稳定,校正集和预测集的标准差分别为0.17和0.39,校正集的相关系数也达到0.988 3。试验结果说明近红外光谱漫透射技术能够快速、无损地检测出苹果的可溶性固形物含量。     

基于近红外光谱漫透射技术的苹果可溶性固形物含量在线检测

为研究苹果的内部品质,提高检测的速度和稳定性,将近红外光谱漫透射技术应用于在线检测研究,并采取偏最小二乘回归(PLSR)算法结合不同光谱预处理方法建立苹果内部的可溶性固形物含量(SSC)的定量模型。结果表明:采用一阶微分结合多元散射校正(MSC)预处理后的模型最稳定,校正集和预测集的标准差分别为0.17和0.39,校正集的相关系数也达到0.988 3。试验结果说明近红外光谱漫透射技术能够快速、无损地检测出苹果的可溶性固形物含量。     

生鲜猪肉细菌总数的高光谱特征参数研究

目的 通过对高光谱数据进行洛伦兹拟合参数的分析, 讨论高光谱技术对生鲜猪肉细菌总数预测的可行性。方法 63个猪肉样品贮存于4 ℃冰箱中, 每天随机取出4块样品, 在400~1100 nm波长范围内获取猪肉表面的高光谱散射图像, 从高光谱图像中提取猪肉的反射光谱曲线, 利用洛伦兹函数进行拟合, 然后用单参数和不同参数结合的方法建立多元线性回归模型。结果 多参数结合的方法比单个参数建立的模型更好, 最好的模型结果是三个参数结合建立模型, 校正集相关系数为0.96, 标准差为0.42; 预测集相关系数为0.89, 标准差为0.46。结论 利用高光谱成像技术结合洛伦兹函数对快速检测猪肉细菌总数具有一定的可行性。     

基于近红外光谱技术的桃品质指标快速检测方法研究

采用傅里叶变化近红外光谱技术建立桃的甜度、酸度和硬度品质参数快速检测方法.采集1 000～2 500nm范围的近红外光谱,选取1 110～2 325nm为分析区域,描述谱峰的归属.以常规分析测定值作建模数据,采用偏最小二乘(PLS)回归法建立桃的品质参数定量分析模型,并考察近红外光谱预处理方法对模型的影响.分别用验证集和校正集样本分析模型预测的准确性.结果显示预测集均方差(RMSEP)分别为0.98、0.309、2.81,校正集均方差(RMSEC)分别为0.258、0.1、1.83,相关系数分别为0.9766、0.8918、0.9497.样本的预测值与真实测定值之间没有显著性差异(P＞0.05).本研究结果表明,采用近红外光谱法可同时测定桃的甜度、酸度和硬度等品质参数.与传统的化学分析方法相比,该方法具有快速、无损、简单等特点.     

虾样品不同采集状态对近红外光谱PLS模型的影响

研究了不同采集状态的虾样品对近红外光谱PLS模型的影响。利用DA7200近红外光谱仪,采集南美白对虾完整虾和虾糜的近红外光谱曲线。采用Unscrambler10.3软件选择最佳光谱预处理方法和最优波段,建立了完整虾和虾糜与挥发性盐基氮(TVB-N)值、菌落总数(TBC)值关联的偏最小二乘(PLS)模型,并对模型进行评价和验证。结果表明:定标集虾糜模型中的校正相关系数rc,校正决定系数Rc2,交叉验证相关系数rv,交叉验证决定系数Rv2,均高于完整虾模型;校正均方根误差RMSEC,校正标准误差SEC,交叉验证均方根误差RMSECV,交叉验证标准误差SECV均低于完整虾模型。验证模型中虾糜预测模型中相关系数r均大于完整虾预测模型,预测均方根误差RMSEP,预测标准误差SEP均低于完整虾预测模型,且虾糜预测模型对TVB-N、TBC值预测值更为准确,表明以虾糜作为近红外光谱采集状态优于完整虾。     

鸡蛋脂肪含量近红外光谱无损检测技术研究

为建立近红外光谱无损检测鸡蛋脂肪含量的方法,在近红外光谱全波段内采集鸡蛋样品的漫反射光谱图,用酸水解法测定鸡蛋样品中的脂肪含量。对采集的光谱进行最小-最大归一化(Min-max Normalization,MMN)、矢量归一化(Vector Normalization,SNV)、平滑、一阶导数(First Derivative,FD)及多元散射校正(Multiplicative Scatter Correction,MSC)处理,用偏最小二乘法(Partial Least Squares,PLS)对鸡蛋脂肪含量建模验证。结果表明,经多元散射校正(MSC)法预处理,偏最小二乘法(PLS)建模以及杠杆校正(Leverage Correction)检验,鸡蛋的脂肪含量与其近红外光谱信号之间存在线性关系,校正集和验证集相关系数R2分别0.947 5,0.906 3,校正均方差RMSEE为0.173 2,预测均方差RMSEP为0.231 4,模型效果最好,可用于鸡蛋中脂肪含量的无损检测。     

基于高光谱散射图像的苹果压缩硬度和汁液含量无损检测

压缩硬度和汁液含量是衡量苹果内部品质的两项重要指标。采用高光谱散射图像技术对苹果压缩硬度和汁液含量进行预测。已有研究表明,高光谱图像含有丰富的波谱信息,光谱值与测量值之间存在严重的非线性关系,简单的线性建模方法不能达到较高的预测精度。最小二乘支持向量机(Least Squares Support Vector Machine,LS_SVM)作为一种非线性建模工具,已用于解决小样本、非线性和高维数等实际问题。针对580个‘RedDelicious’苹果的高光谱散射图像,提取600～1000nm范围内的波谱信息,采用LS_SVM建立苹果的压缩硬度和汁液含量模型。研究结果表明,LS_SVM压缩硬度预测模型的相关系数为Rp=0.795,预测均方差为RMSEP=10.4KN/m,汁液含量的相关系数为Rp=0.568,预测均方差为RMSEP=1.20cm2,高于传统的偏微分最小二乘(PartialLeastSquares,PLS)建立的压缩硬度,模型精度Rp=0.744,RMSEP=11.4KN/m,汁液含量模型精度Rp=0.539,RMSEP=1.23cm2。     

Nondestructive measurement of firmness and soluble solids content for apple fruit using hyperspectral scattering images

Nondestructive sensing is critical to assuring postharvest quality of apple fruit and consumer acceptance and satisfaction. The objective of this research was to use a hyperspectral scattering technique to acquire spectral scattering images from apple fruit and develop a data analysis method relating hyperspectral scattering characteristics to fruit firmness and soluble solids content (SSC). Hyperspectral scattering images were obtained from ‘Golden Delicious’ (GD) and red ‘Delicious’ (RD) apples, which were generated by a broadband beam over the spectral region between 500 nm and 1,000 nm. Mean and standard deviation spectra were extracted from the hyperspectral scattering images. A hybrid method combining the backpropagation feedforward neural network with principal component analysis was used to develop prediction models for fruit firmness and SSC. The neural network models were able to predict fruit firmness with r ² = 0.76 and the standard error of prediction (SEP) of 6.2 N for GD, and r ² = 0.55 and SEP = 6.1 N for RD. Better SSC predictions were obtained with r ² = 0.79 and 0.64 and SEP = 0.72% and 0.81% for GD and RD, respectively. Hyperspectral scattering is promising for assessing internal quality, especially the firmness, of apples. Mention of commercial products is only to provide factual information for the reader and does not imply endorsement of the US Department of Agriculture.     

高光谱图像感兴趣区域对苹果糖度模型的影响

高光谱图像技术作为一种强有力的新兴技术,已应用于食品农产品品质与安全检测研究,然而高光谱图像中感兴趣区域形状大小的选择直接影响着检测的精度和稳定性。首先采集苹果330~1100 nm的高光谱图像,分别提取不同大小的圆形感兴趣区域和方形感兴趣区域的平均光谱,经光谱预处理以消除噪声及无关信息的影响,然后采用偏最小二乘法分别建立苹果的糖度定量分析模型,并以独立样本的预测集进行验证,分析感兴趣区域形状大小对高光谱图像建模精度的影响。结果表明,提取直径为150像素的圆形感兴趣区域建立的苹果糖度模型精度最高,预测能力最强,校正集相关系数Rc为0.9305,校正均方根误差RMSEC为0.4331,预测集相关系数Rp为0.9232,预测均方根误差RMSEP为0.4568。研究表明,针对研究对象选择合适形状和大小的感兴趣区域,对提高模型精度、发挥高光谱图像的技术优势具有重要意义。     

高光谱成像的红提总酸与硬度的预测及其分布可视化

利用高光谱成像技术实现对红提总酸和硬度无损检测和分布可视化。首先,利用高光谱采集生长期360个红提样本在波段450～1 000 nm的高光谱图像信息后用化学方法测定对应样本的总酸,用质构仪测定硬度。采用KS(Kennard-Stone)算法将总样本按照3∶1的比例划分为训练集（270个样本）和测试集（90个样本）。对红提原始光谱数据分别利用标准正态变量变换（standard normal variate transformation,SNV）、卷积平滑（Savitzky-Golay,SG）处理法、多元散射校正（multivariate scatter correction,MSC）、归一化等光谱预处理方法处理,确定最优光谱预处理方法。然后,分别采用一次降维（竞争性自适应重加权算法（competitive adaptive reweighted sampling,CARS）、连续投影算法（successive projections algorithm,SPA）、遗传算法（genetic algorithm,GA）、无信息变量消除法（uninformative variable elim...     

Wavelength Selection of Hyperspectral Scattering Image Using New Semi-supervised Affinity Propagation for Prediction of Firmness and Soluble Solid Content in Apples

Hyperspectral scattering image technology is an effective method for nondestructive measurement of internal qualities of agricultural products. However, hyperspectral scattering images contain a large number of redundant data that affect the detection performance and efficiency. A new semi-supervised affinity propagation (AP) (NSAP) algorithm coupled with partial least square regression was proposed to select the feature wavelengths from the hyperspectral scattering profiles of “Golden Delicious” apples for predicting apple firmness and soluble solid content (SSC). Six hundred apples were analyzed in the experiment, 400 of which were used for the calibration model and the remaining 200 apples were used for the prediction model. Compared with full wavelengths, the number of effective wavelengths for apple firmness and SSC prediction selected by NSAP, respectively, decreased to 28 and 40 %. The root mean square error of prediction decreased from 6.6 to 6.1 N and from 0.66 to 0.63 %, respectively, whereas the correlation coefficient increased from 0.840 to 0.862 and from 0.876 to 0.890, respectively. Better prediction accuracy was achieved by the prediction model using selected wavelengths by NSAP than that by traditional AP, SAP, and genetic algorithm. The NSAP approach provided an effective means of wavelength selection using hyperspectral scattering image technique.     

Predict Compositions and Mechanical Properties of Sugar Beet Using Hyperspectral Scattering

Sucrose, soluble solids, and moisture content and mechanical properties are important quality/property attributes of sugar beet. In this study, hyperspectral scattering images for the spectral region of 500–1000 nm were acquired, from which relative mean spectra were calculated. Prediction models were developed using partial least squares regression for both full spectra and selected wavelengths. The results showed that using relative mean spectra gave good predictions for the moisture, soluble solids, and sucrose content of beet slices with the correlations of 0.75–0.88 and the standard errors of prediction of 0.95–1.08 based on full-spectrum partial least squares regression (PLSR) models. PLSR models using wavelength selection with the uninformative variable elimination (UVE) method produced similar prediction accuracy. However, both modeling approaches gave poor predictions for the mechanical properties of beets with the correlation values of 0.46–0.63. The research demonstrated the potential of hyperspectral scattering imaging for measuring quality attributes of sugar beet.     

PREDICTION OF APPLE FRUIT FIRMNESS BY NEAR‐INFRARED MULTISPECTRAL SCATTERING1

The objective of this research was to predict fruit firmness by developing and evaluating a multispectral imaging system for real time acquisition of scattering images from apple fruit. A circular broadband light beam was used to generate light backscattering at the surface of apple fruit and scattering images were acquired, using a common aperture multispectral imaging system, from Red Delicious apple fruit for wavelengths at 680, 880, 905, and 940 nm. Scattering images were reduced to produce one‐dimensional spectral scattering profiles by radial averaging, which were then input into a backpropagation neural network for predicting apple fruit firmness. The neural network performed best when 10 neurons and 20 epochs were used. With three ratios of spectral profiles involving all four wavelengths, the neural network gave firmness predictions with the correlation of 0.76 and the standard error of 6.2 N for the validation samples.     

Visible/near-infrared hyperspectral imaging prediction of textural firmness of grass carp (Ctenopharyngodon idella) as affected by frozen storage

Textural firmness is a primary determinant of consumer acceptance for evaluating freshness quality of fish fillet flesh. The objective of this study was to investigate the potential of using visible and near-infrared hyperspectral imaging (400–1000 nm) for non-destructive prediction of firmness quality of grass carp fillet as affected by frozen storage. Fillet samples were frozen at − 20 °C for 24 h and then stored at 4 °C for thawing over five days. Hyperspectral images were obtained at different thawing stages and their corresponding spectral data were extracted. Two calibration models were established between the extracted spectral data and the reference firmness values measured by the traditional mechanical method by using partial least squares regression (PLSR) and least-square support vector machine (LS-SVM) analysis. Three approaches of regression coefficients (RC) from PLSR analysis, genetic algorithm (GA) and successive projection algorithm (SPA) were utilized to recognize the most important wavelengths that possessed the greatest influence and sensitivity on the firmness prediction based upon the whole spectral range. By comparing the above-mentioned three variable selection methods, seven optimal wavelengths (450, 530, 550, 616, 720, 955 and 980 nm) were selected by GA and its corresponding simplified prediction model of GA-LS-SVM was also obtained, showing the best performance with the highest determination coefficient (R²_P) of 0.941 and the lowest root mean square error estimated by prediction (RMSEP) of 1.229. The overall results of this study suggested that hyperspectral imaging technique has a potential for fast and non-destructive prediction and analysis of textural firmness of grass carp fillets as affected by frozen storage.     

白酒糟醅中酸度值的高光谱检测方法

酸度值是评价白酒糟醅质量的重要指标之一,为进一步提高糟醅酸度值的检测精度,提出了一种应用高光谱成像技术检测糟醅酸度值的方法.采用高光谱成像系统,在900～1700 nm内采集糟醅样本的光谱信息,并提取全部样本的平均光谱数据.采用3种预处理方法对原始光谱进行预处理,得到多元散射校正(multiplica-tive sca...