Application of Near-Infrared Hyperspectral Imaging for Detection of External Insect Infestations on Jujube Fruit

A hyperspectral imaging system has been built for detecting external insect damage and acquiring reflectance images from jujubes in the near-infrared region of 900–1700 nm. Spectral information was extracted from each jujube, and six optimal wavelengths (987, 1028, 1160, 1231, 1285, and 1464 nm) were obtained using principal component analysis. The first principal component images (PC-1) using the selected six wavelengths were obtained for further image processing. The detection algorithm was then developed based on principal component analysis and two-band ratio (R1160/R1464) coupled with image subtraction algorithm (R1160-R1464). An identification accuracy of 93.1% for insect-infested jujubes and 100% classification rate for the intact ones were achieved. The results of this research demonstrated that it is feasible to discriminate insect-infested jujubes from intact jujubes using the near-infrared hyperspectral imaging technology.     

Prediction of Color and pH of Salted Porcine Meats Using Visible and Near-Infrared Hyperspectral Imaging

A quick, accurate, and reliable method for the evaluation of meat quality during salting stages is essential for quality control and management. This study was carried out to investigate the utility of hyperspectral imaging (HSI) techniques (400–1,000 nm) for predicting the color and pH of salted meat. Specifically, partial least squares regression (PLSR) was applied to the spectral data extracted from the images of the meat to develop statistical models for predicting color and pH. A subset of information-rich wavelengths was identified by principal component analysis (PCA) and used in a regression model. The results from the model with the reduced number of wavelengths generated L*, a*, and pH values with coefficients of determination (R ² _cv) of 0.723, 0.726, and 0.86 and root mean square errors estimated by cross-validation (RMSECV) of 2.898, 1.408, and 0.073, respectively. These values compared favorably with values generated by a PLSR model using all of the wavelengths investigated, illustrating the reasonable accuracy and robustness of the method. The overall results of this study demonstrate the potential of HSI to serve as an objective and nondestructive method for rapid determination of color and pH of porcine meat during the salting process.     

Comparison of Visible and Long-wave Near-Infrared Hyperspectral Imaging for Colour Measurement of Grass Carp (Ctenopharyngodon idella)

This study was conducted to investigate the potential of hyperspectral imaging technique in a rapid and non-invasive manner for measuring colour distribution of grass carp fillets during cold storage. The quantitative calibration models were established between the spectral data extracted from the hyperspectral images and the measured colour reference values by partial least squares regression (PLSR) and least squares support vector machines (LS-SVM). The performance of two spectral ranges of 400–1,000 and 1,000–2,500 nm was compared to select the best spectral range for further colour analysis of grass carp fillets. The LS-SVM model using the whole spectral range possessed better performance than the PLSR model for predicting colour components of L* and a* with higher coefficients of determination (R ² _P) of 0.916 and 0.905 and lower root-mean-square errors of prediction (RMSEPs) of 2.876 and 2.253, respectively. Seven (466, 525, 590, 620, 715, 850 and 955 nm) and five (465, 585, 660, 720 and 950 nm) optimal wavelengths carrying the most important and sensitive information were recognized and selected using successive projections algorithm (SPA) for predicting L* and a*, with R ² _P values of 0.912 and 0.891 being obtained from the optimized SPA-LS-SVM models established based on the selected valuable wavelengths. In addition, the visualization maps of colour distribution of the examined fish fillets were acquired. The overall results of this study demonstrated that hyperspectral imaging technique in the spectral range of 400–1,000 nm has the potential to be used as an objective and promising tool for rapid and non-destructive measurement of colour distribution of grass carp fillets.     

Nondestructive Freshness Discriminating of Shrimp Using Visible/Near-Infrared Hyperspectral Imaging Technique and Deep Learning Algorithm

In this study, visible and near-infrared hyperspectral imaging (HSI) technique combined with deep learning algorithm was investigated for discriminating the freshness of shrimp during cold storage. Shrimps were labeled into two freshness grades (fresh and stale) according to their total volatile basic nitrogen contents. Spectral features were extracted from the HSI data by stacked auto-encoders (SAEs)-based deep learning algorithm and then used to classify the freshness grade of shrimp by a logistic regression (LR)-based deep learning algorithm. The results demonstrated that the SAEs–LR achieved satisfactory total classification accuracy of 96.55 and 93.97% for freshness grade of shrimp in calibration (116 samples) and prediction (116 samples) sets, respectively. An image processing algorithm was also developed for visualizing the classification map of freshness grade. Results confirmed the possibility of rapid and nondestructive detecting freshness grade of shrimp by the combination of hyperspectral imaging technique and deep learning algorithm. The SAEs–LR method adds a new tool for the multivariate analysis of hyperspectral image for shrimp quality inspections.     

Identifying CPPU-Treated Kiwifruits Using Near-Infrared Hyperspectral Imaging Technology

The application of forchlorfenuron (N-(2-chloro-4-pyridyl)-N′-phenylurea), short form CPPU, on kiwifruits has become an important factor that influences kiwifruit economic efficiency and the health development of kiwifruit industry. This study aims to investigate the feasibility of using hyperspectral imaging technology to identify kiwifruits treated with CPPU (named as treated kiwifruits) from kiwifruits without CPPU treatment (named as untreated kiwifruits), and to investigate which model, developed for a single variety or for two varieties together, has better identification performance. Two hundred and forty “Xixuan” kiwifruits and 240 “Huayou” kiwifruits (120 treated kiwifruits and 120 untreated kiwifruits for each variety) were used to obtain hyperspectral from 865.11 to 1711.71 nm. The samples were divided into calibration set and prediction set based on Kennard–Stone method as the ratio of 3:1. Standard normal variate transformation was used to preprocess obtained spectra. Successive projections algorithm (SPA) was applied to extract the characteristic wavelengths from full spectra (FS). Support vector machine (SVM) and extreme learning machine (ELM) modeling methods were used to establish identification models of treated kiwifruits based on FS, characteristic wavelengths extracted by SPA, and universal wavelengths (UWs) extracted from characteristic wavelengths selected by SPA for “Xixuan,” “Huayou,” and two varieties together, respectively. The results showed that the number of characteristic wavelengths selected by SPA were 18, 18, and 21 for “Xixuan,” “Huayou,” and two varieties together, respectively. Five UWs were found for the three different samples. The best model was SPA-ELM for both “Xixuan” (99.8 % accuracy rate for predication set) and “Huayou” (100.0 % accuracy rate for predication set). Models of SPA-SVM and SPA-ELM, whose accuracy rate reached 100 % for both calibration and predication sets, had the best performance when the two varieties were used together. The performances of models built for two varieties together were better than that for “Xixuan,” but they were worse than that for “Huayou.”.The study indicates that NIR hyperspectral imaging technique can be used as a noninvasive method for identifying CPPU-treated kiwifruits from untreated ones, and it is potential to develop a model based on multi-varieties together.     

便携式葡萄专用可见-近红外光谱检测仪器开发与实验

基于可见-近红外光谱技术,研发低成本、便携式葡萄专用多参数检测仪器,用于满足葡萄采后品质快速、无损的检测需求。本仪器选用凹面全息光栅搭配电荷耦合器件的光谱仪作为核心器件,用于获取样品400～1 100 nm的漫反射光谱数据;选用卤素灯作为稳定可靠的光源、低OH的Y型石英光纤作为光传输的可靠媒介,并设计可调型样品池满足不同大小和品种样品的需求,基于Windows系统采用C#撰写的软件性能稳定,便于模型的更新操作。以“美人指”、“白玉霓”两个葡萄品种进行实验,指标参数包含CIE L*a*b*、可溶性固形物含量及总酚含量。结果显示,本仪器基于最小二乘-支持向量机模型对2 个品种的a*值、可溶性固形物、总酚有较好的建模效果,“美人指”各指标的模型决定系数（Rc 2 ）分别为0.91、0.94和0.90;“白玉霓”各指标的模型决定系数分别为0.96、0.99和0.95。最后,利用70 个非建模葡萄样本模型进行外部测试,结果表明“美人指”的a*值、可溶性固形物、总酚3 个指标的预测根均方误差分别为3.15、1.39 °Brix和0.24 g/kg;“白玉霓”3 个指标的预测根均方误差分别为0.78、1.56 °Brix和0.22 g/kg。结果表明,本仪器能完成对葡萄多个理化指标的建模预测,同时样品池的设计能够满足不同品种葡萄的需求。本研究为果蔬专用型近红外仪器的开发提供技术参考。     

Mapping of Fat and Moisture Distribution in Atlantic Salmon Using Near-Infrared Hyperspectral Imaging

A nondestructive and rapid method using near-infrared (NIR) hyperspectral imaging was investigated to determine the spatial distribution of fat and moisture in Atlantic salmon fillets. Altogether, 100 samples were studied, cutting out from different parts of five whole fillets. For each sample, the hyperspectral image was collected with a pushbroom NIR (899–1,694 nm) hyperspectral imaging system followed by chemical analysis to measure its reference fat and moisture contents. Mean spectrum were extracted from the region of interest inside each hyperspectral image. The quantitative relationships between spectral data and the reference chemical values were successfully developed based on partial least squares (PLS) regression with correlation coefficient of prediction of 0.93 and 0.94, and root mean square error of prediction of 1.24 and 1.06 for fat and moisture, respectively. Then the PLS models were applied pixel-wise to the hyperspectral images of the prediction samples to produce chemical images for visualizing fat and moisture distribution. The results were promising and demonstrated the potential of this technique to predict constituent distribution in salmon fillets.     

Classification of Black Beans Using Visible and Near Infrared Hyperspectral Imaging

A rapid and non-destructive method based on the visible and near infrared hyperspectral imaging technique in the wavelength range of 390–1050 nm was investigated for discriminating the varieties of black beans. In total, 300 samples of three varieties were scanned by the visible and near infrared hyperspectral imaging system, and hyperspectral data were analyzed by spectral and image processing technique respectively. A successive projection algorithm was used to obtain 13 characteristic wavelengths (504, 507, 512, 516, 522, 529, 692, 733, 766, 815, 933, 998, and 1000 nm) for spectral analysis. After the processing of successive projection algorithm, optimal image selection was carried out by principal component analysis based on the characteristic wavelengths. The first principal component image was used for the image analysis, whose contribution rate was over 98.34%. Gray level co-occurrence matrix analysis from first principal component image was applied to extract image features including 16 textural features and six morphological features. In this study, partial least squares-discriminate analysis, support vector machine, and K-nearest neighbors were used for model establishments, respectively, based on spectral feature, image feature, and the combination of spectral and image features. The results show that the best correct discrimination rate of 98.33% was achieved by applying combined spectral and image features. The study demonstrated that visible and near infrared hyperspectral imaging technique was potential for rapid classification of black beans, and the performance of the classification model can be improved by the feature combination.     

Detecting Fertility and Early Embryo Development of Chicken Eggs Using Near-Infrared Hyperspectral Imaging

Early detection of infertile and non-hatchable eggs would benefit hatcheries and poultry breeding farms by saving space, handling costs, and preventing contamination from exploder eggs. Therefore, it would be advantageous to the hatchery industry of developing a non-destructive, rapid, and accurate method to detect the fertility and embryo development of eggs. For this purpose, a near-infrared hyperspectral imaging system was developed to detect fertility and early embryo development. A total of 174 white-shell chicken eggs including 156 fertile eggs and 18 infertile eggs were used in this study and all eggs were incubated in a commercial incubator for 4 days. Hyperspectral images were captured for all eggs on each day of incubation. After imaging on each day, developing embryos in randomly selected eggs were stopped by injecting sodium azide (NaN₃). All the eggs were divided into two classes, fertile eggs and non-fertile eggs (including infertile eggs and dead embryos), and the data set of each class varied with day of incubation. The region of interest (ROI) of each hyperspectral image was segmented and the image texture information was extracted from the ROI of spectral images using Gabor filters. Two types of spectral transmission characteristics termed MS and MG, were obtained by averaging the spectral information of ROI and Gabor-filtered ROI, respectively. The dimensionality of the spectral transmission characteristics were reduced by PCA. The first three PCs were used for K-means clustering, as well as the first three bands with maximum responses of each spectral transmission characteristic. The best classification results were 100 % at day 0, 78.8 % at day 1, 74.1 % at day 2, 81.8 % at day 3, and 84.1 % at day 4. A perfect detection of fertility prior to incubation was obtained using only the first three bands of maximum responses of MS. The classification results suggested the usefulness of the image texture information for detection of early embryo development. Promising results were also obtained when only the first three bands with maximum response of spectral transmission characteristics were used, which indicated the potential in applying hyperspectral imaging techniques to develop a real-time system for detecting fertility and early embryo development of chicken eggs.     

Application of Near-Infrared Hyperspectral Imaging with Variable Selection Methods to Determine and Visualize Caffeine Content of Coffee Beans

Hyperspectral imaging covering the spectral range of 874–1734 nm was used to determine caffeine content of coffee beans. Spectral data of 958.24–1628.89 nm were extracted and preprocessed. Partial least squares regression (PLSR) model on the preprocessed full spectra obtained good performance with coefficient of determination of prediction (R ² _p ) of 0.843 and root mean square error of prediction (RMSEP) of 131.904 μg/g. In addition, 10 variable selection methods were applied to select the best optimal wavelengths. The PLSR models on the different optimal wavelengths obtained satisfactory results. The PLSR model on the wavelengths selected by random frog (RF) performed the best, with R ² _p of 0.878 and RMSEP of 116.327 μg/g. The RF wavelength selection combined with the PLSR model also achieved satisfactory visualization of caffeine content between different coffee beans. The overall results indicated that optimal wavelength selection was an efficient method for spectral data preprocessing, and hyperspectral imaging was illustrated as a potential technique for real-time online determination for caffeine content of coffee beans.     

高光谱成像及近红外技术在鸡肉品质无损检测中的应用

高光谱成像与近红外光谱(near infrared spectroscopy,NIR)技术是现代食品检测领域的重要手段,本研究对2种技术在鸡肉品质无损检测中的预测精度进行研究。选用62份新鲜程度不同的鸡胸肉,提取其高光谱感兴趣区域(region of interest,ROI)的光谱曲线,并测定样品的挥发性盐基氮(total volatile base nitrogen,TVB-N)含量和菌落总数(total viable count,TVC),利用OPUS 6.0光谱处理软件搜寻最佳的光谱预处理和波段组合,分别建立2个指标的偏最小二乘法(partial least square,PLS)定量分析模型。NIR样本选用30份新鲜程度不同的鸡胸肉,测定其TVB-N含量和TVC,建立PLS的交叉验证模型。结果表明:利用高光谱的ROI平均光谱建立的TVB-N含量与TVC模型的相关系数(R~2)分别为0.965和0.919,均方根误差(root mean square error of cross validation,RMSECV)分别为0.121和0.215;利用NIR建立的TVB-N含量与TVC预测模型的R2分别为0.801和0.780,RMSECV分别为0.232和0.312。由此可见,基于高光谱的ROI区域光谱建立的预测模型在鸡肉品质无损检测中具有比NIR更高的预测精度。     

高光谱成像技术在红肉食用品质检测中的应用研究进展

高光谱成像技术是一种集光谱技术与计算机视觉技术为一体的无损检测技术,该项技术能快速、全面、无损地获取肉品的内外部信息,在红肉食用品质的检测中具有广泛应用。本文在简述高光谱成像原理的基础上,详述近年来高光谱成像技术在红肉制品食用品质方面的应用,并对该项技术存在的问题及应用前景进行概述,以期为红肉无损检测的研究提供参考。     

高光谱成像技术检测油茶果成熟度

为解决油茶果采摘期判断不准确可能导致的茶油产量降低问题,应用高光谱成像技术结合化学计量法对油茶果成熟度进行定性判别。完成了高光谱图像的曲率校正,分析不同成熟阶段油茶果的光谱特征和理化特征的变化情况。使用4 种不同的分类算法建立基于全波段光谱数据的油茶果成熟度判别模型,发现支持向量机（support vector machine,SVM）模型的分类正确率最高为97%。结合5 种特征变量选择方法对全波段光谱数据进行降维,发现经过竞争性自适应重加权算法（competitive adaptive reweighted sampling,CARS）选择的特征波长建立的模型正确率最高为82%。提取高光谱图像中的颜色特征和纹理特征建立SVM模型后发现,融合颜色特征和光谱特征建立的SVM模型的正确率高于使用单一的光谱特征（经CARS降维）建立的模型正确率：训练集分类正确率为95%,测试集正确率为93%。结果表明,利用高光谱成像技术能够对不同成熟度的油茶果进行较准确的分类,为茶农对油茶果最佳采摘期的判断提供科学依据,在保障茶籽产量最大化、油质最优化等方面具有重要意义。     

高光谱图像技术检测枇杷叶片三萜酸含量及叶面分布

枇杷叶富含三萜酸类化合物,具有较高的药用价值。本研究首先建立枇杷叶高光谱信号与三萜酸含量的对应关系,然后利用高光谱图像包含每个像素点的光谱信号这一独特优势,检测枇杷叶片的三萜酸分布。通过联合区间偏最小二乘法(si PLS)建立三萜酸含量分析模型,结果表明,采用si PLS将全光谱均匀划分11个子区间,选择1、5、6、7联合,主因子数为4 h,建立的si PLS谱区筛选模型预测效果最佳,其交互验证均方根误差(RMSECV)和预测均方根误差(RMSEP)分别为3.392 mg/g和3.731 mg/g,校正集和预测集相关系数分别为0.8449和0.8223。根据si PLS模型计算叶片上所有像素点处的三萜酸含量,并通过伪彩色方法描述叶片中三萜酸含量的分布。研究结果表明,利用高光谱图像技术分析枇杷叶片三萜酸含量及叶面分布是可行的。     

振动胁迫下双孢蘑菇高光谱成像品质检测

为快速有效识别双孢蘑菇轻微损伤,以不同振动时间后不同损伤程度的双孢蘑菇为研究对象,采集400～1 000 nm的完好无损、振动60 s和振动120 s双孢蘑菇的近红外高光谱图像,发现3 种类型的双孢蘑菇在450～750 nm的光谱曲线有明显差异。比较标准正态变量变换、SG（Savitzky-Golay）平滑和多元散射校正等预处理方法,确定SG平滑为最优预处理方法。并将处理后的数据采用连续投影算法和竞争性自适应重加权算法提取不同损伤程度的特征波段;基于灰度共生矩阵提取500 nm波长特征图像感兴趣区域的纹理特征,分别将光谱信息和纹理特征信息作为输入,建立偏最小二乘判别分析（partial least squares-discriminant analysis,PLS-DA）、BP（back propagation）神经网络和极限学习机损伤程度识别模型。结果表明,两种特征集建模,PLS-DA模型均表现出最好的识别效果,PLS-DA模型训练集和测试集平均识别准确率为93.33%、91.11%和88.89%、86.67%。最后基于光谱-纹理融合信息建立PLS-DA模型,训练集和测试集总体识别正确率分别为97.78%、95.56%。结果表明,光谱-纹理融合信息建模预测效果优于单一特征信息建立的判别模型。因此,采用高光谱融合信息建模可以提高不同损伤程度的双孢蘑菇检测精度,为双孢蘑菇贮藏、分类提供理论支撑。     

高光谱成像技术在动物源性食品微生物污染快速检测中的应用进展

高光谱成像(hyperspectral imaging,HSI)技术作为一种无损、快速、准确的检测技术在动物源性食品微生物污染检测方面得到了广泛应用.该技术集图像与光谱技术的优势于一体,可同时检测实验样品的物理特征与化学特征.本文系统地综述HSI原理,及其在动物源性食品微生物(菌落总数、腐败菌、致病菌)污染无损检测方面...     

红葡萄酒中白藜芦醇含量的高光谱快速检测算法优化

将高光谱技术与流化床富集技术相结合,用大孔吸附树脂对干红葡萄酒中的微量白藜芦醇吸附后,采集光谱图像,通过比对多种预处理方法对建模效果的影响进而优选算法。结果表明,采用霍特林T2统计检测方法剔除异常样本,KS算法划分白藜芦醇含量样本集,标准正态变换法预处理光谱数据,建立的标准正态变换-偏最小二乘回归模型预测效果最优,其校正相关系数Rc2为0.813 8,校正均方根误差为0.047 7,预测相关系数Rp2为0.782 4,预测均方根误差为0.050 2,为白藜芦醇的高光谱痕量检测提供理论参考。     

Extraction of Spectral Information from Hyperspectral Data and Application of Hyperspectral Imaging for Food and Agricultural Products

Hyperspectral imaging is built with the aggregation of imaging, spectroscopy and radiometric techniques. This technique observes the sample behaviour when it is exposed to light and interprets the properties of the biological samples. As hyperspectral imaging helps in interpreting the sample at the molecular level, it can distinguish very minute changes in the sample composition from its scatter properties. Hyperspectral data collection depends on several parameters such as electromagnetic spectrum wavelength range, imaging mode and imaging system. Spectral data acquired using a hyperspectral imaging system contain variations due to external factors and imaging components. Moreover, food samples are complex matrices with conditions of surface and internal heterogeneities, which may lead to variations in acquired data. Hence, before extracting information, these variations and noises must be reduced from the data using reference-dependent or reference-independent spectral pre-processing techniques. Using of the entire hyperspectral data for information extraction is tedious and time-consuming. In order to overcome this, exploratory data analysis techniques are used to select crucial wavelengths from the excessive hyperspectral data. Using appropriate chemometric techniques (supervised or unsupervised learning techniques) on this pre-processed hyperspectral data, qualitative or quantitative information from sample can be obtained. Qualitative information for analysing of the chemical composition, detecting of the defects and determining the purity of the food product can be extracted using discriminant analysis techniques. Quantitative information including variation in chemical constituents and contamination levels in food and agricultural sample can be extracted using categorical regression techniques. In combination with appropriate spectra pre-processing and chemometric technique, hyperspectral imaging stands out as an advanced quality evaluation system for food and agricultural products.     

基于特征融合的猪肉新鲜度高光谱图像检测

利用高光谱反射图像技术研究了猪肉新鲜度的无损检测。采集了180个猪肉样本在400~1 000 nm范围内的高光谱反射图像,提取了高光谱图像的光谱均值和熵两类特征;分别利用连续投影算法、主成分分析,以及连续投影算法结合主成分分析3种特征降维方法,提取了反映肉类新鲜度信息的重要特征变量;并建立了这些特征变量与挥发性盐基氮(TVB-N)的最小二乘支持向量机(LSSVM)预测模型;在此基础上提出了猪肉TVB-N含量的可视化检测方法。研究结果表明:相比于单一特征模型,利用光谱均值和熵融合特征的LSSVM模型可显著提高模型的准确度;连续投影算法结合主成分分析的特征降维方法,可显著降低模型的复杂度,提高模型准确度。利用光谱均值和熵两类特征,通过连续投影算法和主成分分析相结合的特征降维方法所建立的LSSVM预测模型,可取得最佳的预测准确度,其预测集的均方根误差RMSEP为1.96,相关系数(RP)为0.948,剩余预测偏差(RPD)为3.12,可满足实际检测需要。建立在此基础上的可视化方法,可直观显示肉类的腐败区域和程度。