Green analytical assay for the viability assessment of single maize seeds using double-threshold strategy for catalase activity and malondialdehyde content.

The development of nondestructive technology for the detection of seed viability is challenging. In this study, to establish a green and effective method for the viability assessment of single maize seeds, a two-stage seed viability detection method was proposed. The catalase (CAT) activity and malondialdehyde (MDA) content were selected as the most key biochemical components affecting maize seed viability, and regression prediction models were developed based on their hyperspectral information and a data fusion strategy. Qualitative discrimination models for seed viability evaluation were constructed based on the predicted response values of the selected key biochemical components. The results showed that the double components thresholds strategy achieved the highest discrimination accuracy (92.9%), providing a crucial approach for the rapid and environmentally friendly detection of seed viability.

Discrimination of New and Aged Seeds Based on On-Line Near-Infrared Spectroscopy Technology Combined with Machine Learning.

The harvest year of maize seeds has a significant impact on seed vitality and maize yield. Therefore, it is vital to identify new seeds. In this study, an on-line near-infrared (NIR) spectra collection device (899-1715 nm) was designed and employed for distinguishing maize seeds harvested in different years. Compared with least squares support vector machine (LS-SVM), k-nearest neighbor (KNN), and extreme learning machine (ELM), the partial least squares discriminant analysis (PLS-DA) model has the optimal recognition performance for maize seed harvest years. Six different preprocessing methods, including Savitzky-Golay smoothing (SGS), standard normal variate transformation (SNV), multiplicative scatter correction (MSC), Savitzky-Golay 1 derivative (SG-D1), Savitzky-Golay 2 derivative (SG-D2), and normalization (Norm), were used to improve the quality of the spectra. The Monte Carlo cross-validation uninformative variable elimination (MC-UVE), competitive adaptive reweighted sampling (CARS), bootstrapping soft shrinkage (BOSS), successive projections algorithm (SPA), and their combinations were used to obtain effective wavelengths and decrease spectral dimensionality. The MC-UVE-BOSS-PLS-DA model achieved the classification with an accuracy of 88.75% using 93 features based on Norm preprocessed spectral data. This study showed that the self-designed NIR collection system could be used to identify the harvested years of maize seed.

Monitoring the major taste components during black tea fermentation using multielement fusion information in decision level.

Hitherto, the intelligent detection of black tea fermentation quality is still a thought-provoking problem because of one-side sample information and poor model performance. This study proposed a novel method for the prediction of major chemical components including total catechins, soluble sugar and caffeine using hyperspectral imaging technology and electrical properties. The multielement fusion information were used to establish quantitative prediction models. The performance of model using multielement fusion information was better than that of model using single information. Subsequently, the stacking combination model using fusion data combined with feature selection algorithms for evaluating the fermentation quality of black tea. Our proposed strategy achieved better performance than classical linear and nonlinear algorithms, with the correlation coefficient of the prediction set (Rp) for total catechins, soluble sugar and caffeine being 0.9978, 0.9973 and 0.9560, respectively. The results demonstrated that our proposed strategy could effectively evaluate the fermentation quality of black tea.

Qualitative and quantitative detection of aflatoxins B1 in maize kernels with fluorescence hyperspectral imaging based on the combination method of boosting and stacking.

The most widespread, toxic, and harmful toxin is aflatoxins B1 (AFB1). The fluorescence hyperspectral imaging (HSI) system was employed for AFB1 detection in this study. This study developed the under sampling stacking (USS) algorithm for imbalanced data. The results indicated that the USS method combined with ANOVA for featured wavelength achieved the best performance with the accuracy of 0.98 for 20 or 50 µg /kg threshold using endosperm side spectra. As for the quantitative analysis, a specified function was used to compress AFB1 content, and the combination of boosting and stacking was used for regression. The support vector regression (SVR)-Boosting, Adaptive Boosting (AdaBoost), and extremely randomized trees (Extra-Trees)-Boosting were used as the base learner, while the K nearest neighbors (KNN) algorithm was used as the meta learner could obtain the best results, with the correlation coefficient of prediction (Rp) was 0.86. These results provided the basis for developing AFB1 detection and estimation technologies.

Real-Time Grading of Defect Apples Using Semantic Segmentation Combination with a Pruned YOLO V4 Network.

At present, the apple grading system usually conveys apples by a belt or rollers. This usually leads to low hardness or expensive fruits being bruised, resulting in economic losses. In order to realize real-time detection and classification of high-quality apples, separate fruit trays were designed to convey apples and used to prevent apples from being bruised during image acquisition. A semantic segmentation method based on the BiSeNet V2 deep learning network was proposed to segment the defective parts of defective apples. BiSeNet V2 for apple defect detection obtained a slightly better result in MPA with a value of 99.66%, which was 0.14 and 0.19 percentage points higher than DAnet and Unet, respectively. A model pruning method was used to optimize the structure of the YOLO V4 network. The detection accuracy of defect regions in apple images was further improved by the pruned YOLO V4 network. Then, a surface mapping method between the defect area in apple images and the actual defect area was proposed to accurately calculate the defect area. Finally, apples on separate fruit trays were sorted according to the number and area of defects in the apple images. The experimental results showed that the average accuracy of apple classification was 92.42%, and the F1 score was 94.31. In commercial separate fruit tray grading and sorting machines, it has great application potential.

Effects of Orientations and Regions on Performance of Online Soluble Solids Content Prediction Models Based on Near-Infrared Spectroscopy for Peaches.

Predicting the soluble solid content (SSC) of peaches based on visible/near infrared spectroscopy has attracted widespread attention. Due to the anisotropic structure of peach fruit, spectra collected from different orientations and regions of peach fruit will bring variations in the performance of SSC prediction models. In this study, the effects of spectra collection orientations and regions on online SSC prediction models for peaches were investigated. Full transmittance spectra were collected in two orientations: stem-calyx axis vertical (Orientation1) and stem-calyx axis horizontal (Orientation2). A partial least squares (PLS) method was used to evaluate the spectra collected in the two orientations. Then, each peach fruit was divided into three parts. PLS was used to evaluate the corresponding spectra of combinations of these three parts. Finally, effective wavelengths were selected using the successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS). Both orientations were ideal for spectra acquisition. Regions without peach pit were ideal for modeling, and the effective wavelengths selected by the SPA led to better performance. The correlation coefficient and root mean square error of validation of the optimal models were 0.90 and 0.65%, respectively, indicating that the optimal model has potential for online prediction of peach SSC.

Rapid and Non-destructive Classification of New and Aged Maize Seeds Using Hyperspectral Image and Chemometric Methods.

The aged seeds have a significant influence on seed vigor and corn growth. Therefore, it is vital for the planting industry to identify aged seeds. In this study, hyperspectral reflectance imaging (1,000-2,000 nm) was employed for identifying aged maize seeds using seeds harvested in different years. The average spectra of the embryo side, endosperm side, and both sides were extracted. The support vector machine (SVM) algorithm was used to develop classification models based on full spectra to evaluate the potential of hyperspectral imaging for maize seed detection and using the principal component analysis (PCA) and ANOVA to reduce data dimensionality and extract feature wavelengths. The classification models achieved perfect performance using full spectra with an accuracy of 100% for the prediction set. The performance of models established with the first three principal components was similar to full spectrum models, but that of PCA loading models was worse. Compared to other spectra, the two-band ratio (1,987 nm/1,079 nm) selected by ANOVA from embryo-side spectra achieved a better classification accuracy of 95% for the prediction set. The image texture features, including histogram statistics (HS) and gray-level co-occurrence matrix (GLCM), were extracted from the two-band ratio image to establish fusion models. The results demonstrated that the two-band ratio selected from embryo-side spectra combined with image texture features achieved the classification of maize seeds harvested in different years with an accuracy of 97.5% for the prediction set. The overall results indicated that combining the two wavelengths with image texture features could detect aged maize seeds effectively. The proposed method was conducive to the development of multi-spectral detection equipment.

Variety classification of coated maize seeds based on Raman hyperspectral imaging.

As an essential factor in quality assessment of maize seeds, variety purity profoundly impacts final yield and farmers' economic benefits. In this study, a novel method based on Raman hyperspectral imaging system was applied to achieve variety classification of coated maize seeds. A total of 760 maize seeds including 4 different varieties were evaluated. Raman spectral data of 400-1800 cm-1 were extracted and preprocessed. Variable selection methods involved were modified competitive adaptive reweighted sampling (MCARS), successive projections algorithm (SPA), and their combination. In addition, MCARS was proposed for the first time in this paper as a stable search technology. The performance of support vector machine (SVM) models optimized by genetic algorithm (GA) was analyzed and compared with models based on random forest (RF) and back-propagation neural network (BPNN). Same models based on Vis-NIR spectral data were also established for comparison. Results showed that the MCARS-GA-SVM model based on Raman spectral data obtained the best performance with calibration accuracy of 99.29% and prediction accuracy of 100%, which were stable and easily replicated. In addition, the accuracy on the independent validation set was 96.88%, which proved that the model can be applied in practice. A more simplified MCARS-SPA-GA-SVM model, which contained only 3 variables, had more than 95% accuracy on each data set. This procedure can help to develop a real-time detection system to classify coated seed varieties with high accuracy, which is of great significance for assessing variety purity and increasing crop yield.

Robustness and accuracy evaluation of moisture prediction model for black tea withering process using hyperspectral imaging.

The rapid and non-destructive detection of moisture in withering leaves is an unsolved problem because the leaves are stacked together and have random orientation. To address this issue, this study aimed to establish more robust and accurate models. The performance of front side, back side and multi-region models were compared, and the front side model showed the worst transferability. Therefore, five effective wavelength (EW) selection algorithms were combined with a successive projection algorithm (SPA) to select EWs. It was found that the shuffled frog leaping algorithm (SFLA) combined with SPA was the best method for the front side model for moisture analyses. Based on the selected EWs, the extreme learning machine (ELM) became the model with the best self-verification result. Subsequently, moisture distribution maps of withering leaves were successfully generated. Considering the processing demand of withering leaves, local region models developed based on partial least squares and the SFLA-SPA method were applied to predict the moisture of withering leaves in the local and stacked region. The results showed that the RPD, Rcv and Rp values were above 1.6, 0.870 and 0.897, respectively. These results provide a useful reference for the non-destructive detection of moisture in withering leaves.

Integration of textural and spectral features of Raman hyperspectral imaging for quantitative determination of a single maize kernel mildew coupled with chemometrics.

Maize mildew is a common phenomenon and it is essential to detect the mildew of a single maize kernel and prevent mildew from spreading around. In this study, a line-scanning Raman hyperspectral imaging system was applied to detect fungal spore quantity of a single maize kernel. Raman spectra were extracted while textural features were obtained to depict the maize mildew. Three kinds of modeling algorithms were used to establish the quantitative model to determine the fungal spore quantity of a single maize kernel. Then competitive adaptive reweighted sampling (CARS) was used to optimize characteristic variables. The optimal detection model was established with variables selected from the combination of Raman spectra and textural variance feature by PLSR. Results indicated that it was feasible to detect the fungal spore quantity of a single maize kernel by Raman hyperspectral technique. The study provided an in-situ and nondestructive alternative to detect fungal spore quantity.

Online Detection of Watercore Apples by Vis/NIR Full-Transmittance Spectroscopy Coupled with ANOVA Method.

Watercore is an internal physiological disorder affecting the quality and price of apples. Rapid and non-destructive detection of watercore is of great significance to improve the commercial value of apples. In this study, the visible and near infrared (Vis/NIR) full-transmittance spectroscopy combined with analysis of variance (ANOVA) method was used for online detection of watercore apples. At the speed of 0.5 m/s, the effects of three different orientations (O1, O2, and O3) on the discrimination results of watercore apples were evaluated, respectively. It was found that O3 orientation was the most suitable for detecting watercore apples. One-way ANOVA was used to select the characteristic wavelengths. The least squares-support vector machine (LS-SVM) model with two characteristic wavelengths obtained good performance with the success rates of 96.87% and 100% for watercore and healthy apples, respectively. In addition, full-spectrum data was also utilized to determine the optimal two-band ratio for the discrimination of watercore apples by ANOVA method. Study showed that the threshold discrimination model established based on O3 orientation had the same detection accuracy as the optimal LS-SVM model for samples in the prediction set. Overall, full-transmittance spectroscopy combined with the ANOVA method was feasible to online detect watercore apples, and the threshold discrimination model based on two-band ratio showed great potential for detection of watercore apples.

Detection of early decay on citrus using LW-NIR hyperspectral reflectance imaging coupled with two-band ratio and improved watershed segmentation algorithm.

Decay is a serious problem in citrus storage and transportation. However, the automatic detection of decayed citrus remains a problem. In this study, the long wavelength near-infrared (LW-NIR) hyperspectra reflectance images (1000-1850 nm) of oranges were obtained, and an effective method to detect decayed citrus was proposed. Three effective wavelength selection algorithms and two classification algorithms were used to build decay detection models in pixel-level, as well as the two-band ratio images, pseudo-color image enhancement and improved watershed segmentation were used to build decay detection models in image-level. The image-level detection method proposed in this study obtained a total success rate of 92% for all fruit, indicating its potential to detect decayed oranges online. Moreover, the LW-NIR hyperspectral reflectance imaging is verified as a useful method to detect surface defects of fruits.

Application of long-wave near infrared hyperspectral imaging for determination of moisture content of single maize seed.

Moisture content (MC) is one of the most important factors for assessment of seed quality. However, the accurate detection of MC in single seed is very difficult. In this study, single maize seed was used as research object. A long-wave near infrared (LWNIR) hyperspectral imaging system was developed for acquiring reflectance images of the embryo and endosperm side of maize seed in the spectral range of 930-2548 nm, and the mixed spectra were extracted from both side of maize seeds. Then, Full-spectrum models were established and compared based on different types of spectra. It showed that models established based on spectra of the embryo side and mixed spectra obtained better performance than the endosperm side. Next, a combination of competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) was proposed to select the most effective wavelengths from full-spectrum data. In order to explore the stableness of wavelength selection algorithm, these methods were used for 200 independent experiments based on embryo side and mixed spectra, respectively. Each selection result was used as input of partial least squares regression (PLSR) and least squares support vector machine (LS-SVM) to build calibration models for determining the MC of single maize seed. Results indicated that the CARS-SPA-LS-SVM model established with mixed spectra was optimal for MC prediction in all models by considering the accuracy, stableness and complexity of models. The prediction accuracy of CARS-SPA-LS-SVM model is Rpre = 0.9311 ± 0.0094 and RMSEP = 1.2131 ± 0.0702 in 200 independent assessment. The overall study revealed that the long-wave near infrared hyperspectral imaging can be used to non-invasively and fast measure the MC in single maize seed and a robust and accurate model could be established based on CARS-SPA-LS-SVM method coupled with mixed spectral. These results can provide a useful reference for assessment of other internal quality attributes (such as starch content) of single maize seed.

Nondestructive evaluation of soluble solids content in tomato with different stage by using Vis/NIR technology and multivariate algorithms.

In this study Vis/NIR spectroscopy was applied to evaluate soluble solids content (SSC) of tomato. A total of 168 tomato samples with five different maturity stages, were measured by two developed systems with the wavelength ranges of 500-930 nm and 900-1400 nm, respectively. The raw spectral data were pre-processed by first derivative and standard normal variate (SNV), respectively, and then the effective wavelengths were selected using competitive adaptive reweighted sampling (CARS) and random frog (RF). Partial least squares (PLS) and least square-support vector machines (LS-SVM) were employed to build the prediction models to evaluate SSC in tomatoes. The prediction results revealed that the best performance was obtained using the PLS model with the optimal wavelengths selected by CARS in the range of 900-1400 nm (Rp = 0.820 and RMSEP = 0.207 °Brix). Meanwhile, this best model yielded desirable results with Rp and RMSEP of 0.830 and 0.316 °Brix, respectively, in 60 samples of the independent set. The method proposed from this study can provide an effective and quick way to predict SSC in tomato.

Non-destructive analysis of germination percentage, germination energy and simple vigour index on wheat seeds during storage by Vis/NIR and SWIR hyperspectral imaging.

Two hyperspectral imaging (HSI) systems, visible/near infrared (Vis/NIR, 304-1082 nm) and short wave infrared (SWIR, 930-2548 nm), were used for the first time to comprehensively predict the changes in quality of wheat seeds based on three vigour parameters: germination percentage (GP, reflecting the number of germinated seedling), germination energy (GE, reflecting the speed and uniformity of seedling emergence), and simple vigour index (SVI, reflecting germination percentage and seedling weight). Each sample contained a small number of wheat seeds, which were obtained by high temperature and humidity-accelerated aging (0, 2, and 3 days) to simulate storage. The spectra of these samples were collected using HSI systems. After collection, each seed sample underwent a standard germination test to determine their GP, GE, and SVI. Then, several pretreatment methods and the partial least-squares regression algorithm (PLS-R) were used to establish quantitative models. The models for the Vis/NIR region obtained excellent performance, and most effective wavelengths (EWs) were selected in the Vis/NIR region by the successive projections algorithm (SPA) and regression coefficients (RC). Subsequently, PLS-R-RC models using selected wavebands (sixteen wavebands for GP, 14 wavebands for GE, and 16 wavebands for SVI) exhibited similar performance to the PLS-R models based on the full wavebands. The best R2 results obtained in the simplified models' prediction sets were 0.921, 0.907, and 0.886, with RMSE values of 4.113%, 5.137%, and 0.024, for GP, GE, and SVI, respectively. Distribution maps of GP, GE, and SVI were produced by applying these simplified PLS models. By interpreting the EWs and building prediction models, soluble protein and sugar content were demonstrated to have a relationship with spectral information. In summary, the present results lay a foundation towards the development of a significantly simpler, more comprehensive, and non-destructive hyperspectral-based sorting system for determining the vigour of wheat seeds.

Data Fusion of Two Hyperspectral Imaging Systems with Complementary Spectral Sensing Ranges for Blueberry Bruising Detection.

Currently, the detection of blueberry internal bruising focuses mostly on single hyperspectral imaging (HSI) systems. Attempts to fuse different HSI systems with complementary spectral ranges are still lacking. A push broom based HSI system and a liquid crystal tunable filter (LCTF) based HSI system with different sensing ranges and detectors were investigated to jointly detect blueberry internal bruising in the lab. The mean reflectance spectrum of each berry sample was extracted from the data obtained by two HSI systems respectively. The spectral data from the two spectroscopic techniques were analyzed separately using feature selection method, partial least squares-discriminant analysis (PLS-DA), and support vector machine (SVM), and then fused with three data fusion strategies at the data level, feature level, and decision level. The three data fusion strategies achieved better classification results than using each HSI system alone. The decision level fusion integrating classification results from the two instruments with selected relevant features achieved more promising results, suggesting that the two HSI systems with complementary spectral ranges, combined with feature selection and data fusion strategies, could be used synergistically to improve blueberry internal bruising detection. This study was the first step in demonstrating the feasibility of the fusion of two HSI systems with complementary spectral ranges for detecting blueberry bruising, which could lead to a multispectral imaging system with a few selected wavelengths and an appropriate detector for bruising detection on the packing line.

Rapid and visual detection of the main chemical compositions in maize seeds based on Raman hyperspectral imaging.

Rapid and visual detection of the chemical compositions of plant seeds is important but difficult for a traditional seed quality analysis system. In this study, a custom-designed line-scan Raman hyperspectral imaging system was applied for detecting and displaying the main chemical compositions in a heterogeneous maize seed. Raman hyperspectral images collected from the endosperm and embryo of maize seed were acquired and preprocessed by Savitzky-Golay (SG) filter and adaptive iteratively reweighted Penalized Least Squares (airPLS). Three varieties of maize seeds were analyzed, and the characteristics of the spectral and spatial information were extracted from each hyperspectral image. The Raman characteristic peaks, identified at 477, 1443, 1522, 1596 and 1654 cm-1 from 380 to 1800 cm-1 Raman spectra, were related to corn starch, mixture of oil and starch, zeaxanthin, lignin and oil in maize seeds, respectively. Each single-band image corresponding to the characteristic band characterized the spatial distribution of the chemical composition in a seed successfully. The embryo was distinguished from the endosperm by band operation of the single-band images at 477, 1443, and 1596 cm-1 for each variety. Results showed that Raman hyperspectral imaging system could be used for on-line quality control of maize seeds based on the rapid and visual detection of the chemical compositions in maize seeds.

A bi-layer model for nondestructive prediction of soluble solids content in apple based on reflectance spectra and peel pigments.

Hyperspectral imaging technology was used to investigate the effect of various peel colors on soluble solids content (SSC) prediction model and build a SSC model insensitive to the color distribution of apple peel. The SSC and peel pigments were measured, effective wavelengths (EWs) of SSC and pigments were selected from the acquired hyperspectral images of the intact and peeled apple samples, respectively. The effect of pigments on the SSC prediction was studied and optimal SSC EWs were selected from the peel-flesh layers spectra after removing the chlorophyll and anthocyanin EWs. Then, the optimal bi-layer model for SSC prediction was built based on the finally selected optimal SSC EWs. Results showed that the correlation coefficient of prediction, root mean square error of prediction and selected bands of the bi-layer model were 0.9560, 0.2528 and 41, respectively, which will be more acceptable for future online SSC prediction of various colors of apple.

[Assessment of Influence Detective Position Variability on Precision of Near Infrared Models for Soluble Solid Content of Watermelon].

Non-destructive detection for soluble solids content (SSC) is important to improve watermelon's internal quality, which attracts more and more attention from consumers. In order to realize the precise detection for SSC of mini watermelon's whole surface by using Near-infrared (NIR) spectroscopy and reduce the influence of detective position variability on the accuracy of NIR prediction model for SSC, the diffused transmission spectra and soluble solids content were collected from three different detective positions of 'jingxiu' watermelon, including the equator, calyx and stem. The prediction models of single detective position and mixed three detective positions for SSC were established with Partial least square (PLS). Successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were adopted to select effective variables of NIR spectroscopy for SSC of watermelon as well. The results showed that the prediction model of mixed three detective positions was better than the model of single detective position. Meanwhile, 42 characteristic variables of NIR spectroscopy selected with CARS were used to establish PLS prediction model for SSC. The prediction model was simplified significantly and the prediction accuracy for SSC was improved greatly. The correlation coefficient of prediction (RP) and root mean square error of prediction (RMSEP) by CARS-PLS were 0.892, 0.684 °Brix for the equator, 0.905, 0.621 °Brix for the calyx, 0.899, 0.721 °Brix for the stem, respectively. However, the prediction result of SPA-PLS established by 19 characteristic wavelength variables of NIR spectroscopy was bad for the equator, calyx and stem detective positions. The correlation coefficient of prediction (RP) is less than 0.752 and root mean square error of prediction (RMSEP) is relatively high. It was proposed that the PLS prediction model established by mixed three different detective positions with effective characteristic wavelength variables selected by CARS can improve the prediction accuracy for SSC. And the CARS-PLS prediction model can achieve fast and precise detection for SSC of mini watermelon's whole surface. The influence of detective position variability on the accuracy of NIR prediction model could be reduced simultaneously. This paper could provide theoretical basis for calibrating NIR prediction model for SSC of mini watermelon. It also could provide reference for developing the portable and non-destructive detection equipment for soluble solids content of mini watermelon's whole surface.

Measuring the Moisture Content in Maize Kernel Based on Hyperspctral Image of Embryo Region.

Maize is among the most important economic corps in China while moisture content is a critical parameterin the process of storage and breeding. To measure the moisture content in maize kernel, a near-infrared hyperspectral imaging system has been built to acquire reflectance images from maize kernel samples in the spectral region between 1 000 and 2 500 nm. Near-infrared hyperspectral information of full surface and embryo of maize kernel were firstly extracted based on band ratio coupled with a simple thresholding method and the spectra analysis between moisture content in maize kernel and embryo was performed. The characteristic bands were then selected with the help of Competitive Adaptive Reweighted Sampling (CARS), Genetic Algorithm (GA) and Successive Projection Algorithm (SPA). Finally, these selected variables were used as the inputs to build Partial Least Square (PLS) models for determining the moisture content of maize kernel. In this study, a significant relation, which the spectral reflectance decreases as moisture content increase, between moisture content and spectral of embryo in maize kernel was observed. For the investigated independent test samples, all the proposed regression models, namely CARS-PLS, GA-PLS and SPA-PLS, achieved a good performance by using the information of embryo region. The correlation coefficient (Rp) and Root Mean Squared Error of Prediction (RMSEP) and number of characteristic wavelength for the prediction set were 0.931 2, 0.315 3, 9 and 0.917 6, 0.336 9, 14 and 0.922 7, 0.336 6, 16 for CARS-PLS, GA-PLS and SPA-PLS models, respectively. And, compared with models obtained by full surface spectral information, less characteristic wavelengths is used for development of CARS-PLS, GA-PLS and SPA-PLS models, while similar results were obtained. Comprehensively analyzing to both model accuracy and model complexity, SPA-PLS model by using embryo region information achieved the best result. Wavelengths at 1 197，1 322 and 1 495 nm were applied to extracted the information of embryo region, and the bands at 1 322, 1 342, 1 367, 1 949, 2 070 and 2 496 nm were used to establish the SPA-PLS model. These results demonstrated that near-infrared hyperspectral information from embryo region is more effective for determination of moisture nondestructive in maize kernel.