Non-destructive Identifying Level of Browning Development in Button Mushroom (Agaricus bisporus) Using Hyperspectral Imaging Associated with Chemometrics

Potential of hyperspectral imaging for nondestructive determination of α-farnesene and conjugated trienol content in 'Yali' pear

The sesquiterpene α-farnesene and its corresponding oxidation products, namely conjugated trienols (CTols) is well known to be correlated with the development of superficial scald, a typical physiological disorder after a long term of cold storage in pear fruit. In this work, hyperspectral imaging (HSI) technology was used for nondestructive predicting of α-farnesene and CTols [CT258, CT281 and CT(281-290)] content in 'Yali' pear. In order to obtain the best performance of calibration model and simplify the calibration model further, various preprocessing methods together with their combinations and different wavelength selection algorithms, including successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS) and uninformative variable elimination (UVE), were investigated and compared based on linear partial least square regression (PLSR) and nonlinear least square support vector machine (LS-SVM) models, respectively. In conclusion, compared to the PLSR models, the results of LS-SVM models based on original and preprocessing methods performed better for the prediction of α-farnesene and CTols, while the performance of LS-SVM models based on the selected characteristic wavelengths were worse. For α-farnesene, the best result was obtained by LS-SVM model based on MSC-FD pretreatment with the RPD value of 2.6, Rp = 0.925 and RMSEP = 4.387 nmol cm-2. And for CTols, CT281 performed better compared with CT258 and CT(281-290), achieving the result with RPD = 2.4, Rp = 0.913 and RMSEP = 2.734 nmol cm-2 based on LS-SVM model combined with SD pretreatment. The overall results illustrated HSI technology could be used for rapid and nondestructive prediction of α-farnesene and CTols in 'Yali' pear, which would be helpful for supporting postharvest decision systems.

Towards a Multispectral Imaging System for Spatial Mapping of Chemical Composition in Fresh-Cut Pineapple (Ananas comosus)

With increasing public demand for ready-to-eat fresh-cut fruit, the postharvest industry requires the development and adaptation of monitoring technologies to provide customers with a product of consistent quality. The fresh-cut trade of pineapples (Ananas comosus) is on the rise, favored by the sensory quality of the product and mechanization of the cutting process. In this paper, a multispectral imaging-based approach is introduced to provide distribution maps of moisture content, soluble solids content, and carotenoids content in fresh-cut pineapple. A dataset containing hyperspectral images (380-1690 nm) and reference measurements in 10 regions of interest of 60 fruit (n = 600) was prepared. Ranking and uncorrelatedness (based on ReliefF algorithm) and subset selection (based on CfsSubset algorithm) approaches were applied to find the most informative wavelengths in which bandpass optical filters or light sources are commercially available. The correlation coefficient and error metrics obtained by cross-validated multilayer perceptron neural network models indicated that the superior selected wavelengths (495, 500, 505, 1215, 1240, and 1425 nm) resulted in prediction of moisture content with R = 0.56, MAPE = 1.92%, soluble solids content with R = 0.52, MAPE = 14.72%, and carotenoids content with R = 0.63, MAPE = 43.99%. Prediction of chemical composition in each pixel of the multispectral images using the calibration models yielded spatially distributed quantification of the fruit slice, spatially varying according to the maturation of single fruitlets in the whole pineapple. Calibration models provided reliable responses spatially throughout the surface of fresh-cut pineapple slices with a constant error. According to the approach to use commercially relevant wavelengths, calibration models could be applied in classifying fruit segments in the mechanized preparation of fresh-cut produce.

Quality Information Detection of Agaricus bisporus Based on a Portable Spectrum Acquisition Device

As one of the most popular edible fungi in the market, the quality of Agaricus bisporus will determine its sales volume. Therefore, to achieve rapid and nondestructive testing of the quality of Agaricus bisporus, this study first built a portable spectrum acquisition device for Agaricus bisporus. The Ocean Spectromeper was used to calibrate the spectral data of the device, and the linear regression analysis method was combined to analyze the two. The results showed that the Pearson correlation coefficient of significance between the two was 0.98. Then, the spectral data of Agaricus bisporus were collected, the spectral characteristic wavelength of Agaricus bisporus was extracted by the SPA and PCA algorithms, and the moisture content and whiteness prediction models based on a BP neural network and PLSR, respectively, were built. The parameters of the BP neural network model were optimized by SSA. The R² values for the final moisture content and the predicted whiteness were 0.95 and 0.99, and the RMSE values were 5.04% and 0.60, respectively. The results show that the portable spectral acquisition and analysis device can be used for the accurate and rapid quality detection of Agaricus bisporus.

Non-destructive monitoring of quality attributes kinetics during the drying process: A case study of celeriac slices and the model generalisation in selected commodities

The potential of Visual-NIR hyperspectral imaging (VNIR-HSI, 425-1700 nm) to predict celeriac quality attributes during the drying process was investigated. The HSI-Gaussian Process Regression (GPR) fusion method excellently predicted moisture content (MC, R² ≈ 1.00, RMSE = 0.77 g_w 100 g_s^-1) and water activity (a_w, R² = 0.98, RMSE = 0.04). Moreover, the rehydration ratio (RR, R² = 0.89, RMSE = 0.04) and colour indices (R² = 0.80-0.93, RMSE = 0.17-1.45) were reasonably predicted. However, antioxidant activity (AA) and total phenolic compounds (TPC) were poorly predicted. These results are potentially due to MC variations dominating the NIR region, masking phenolic compounds. Finally, the celeriac-based-trained model was assessed by predicting the MC of apple, cocoyam, and carrot slices. The results were encouraging; however, a GPR model trained on the data of all four commodities was more robust (R² ≈ 1.00, RMSE = 1-2 g_w 100 g_s^-1).

Classification of Granite Soils and Prediction of Soil Water Content Using Hyperspectral Visible and Near-Infrared Imaging

Soil water content is one of the most important physical indicators of landslide hazards. Therefore, quickly and non-destructively classifying soils and determining or predicting water content are essential tasks for the detection of landslide hazards. We investigated hyperspectral information in the visible and near-infrared regions (400–1000 nm) of 162 granite soil samples collected from Seoul (Republic of Korea). First, effective wavelengths were extracted from pre-processed spectral data using the successive projection algorithm to develop a classification model. A gray-level co-occurrence matrix was employed to extract textural variables, and a support vector machine was used to establish calibration models and the prediction model. The results show that an optimal correct classification rate of 89.8% could be achieved by combining data sets of effective wavelengths and texture features for modeling. Using the developed classification model, an artificial neural network (ANN) model for the prediction of soil water content was constructed. The input parameter was composed of Munsell soil color, area of reflectance (near-infrared), and dry unit weight. The accuracy in water content prediction of the developed ANN model was verified by a coefficient of determination and mean absolute percentage error of 0.91 and 10.1%, respectively.

Hyperspectral Imaging Analysis for the Classification of Soil Types and the Determination of Soil Total Nitrogen

Soil is an important environment for crop growth. Quick and accurately access to soil nutrient content information is a prerequisite for scientific fertilization. In this work, hyperspectral imaging (HSI) technology was applied for the classification of soil types and the measurement of soil total nitrogen (TN) content. A total of 183 soil samples collected from Shangyu City (People's Republic of China), were scanned by a near-infrared hyperspectral imaging system with a wavelength range of 874-1734 nm. The soil samples belonged to three major soil types typical of this area, including paddy soil, red soil and seashore saline soil. The successive projections algorithm (SPA) method was utilized to select effective wavelengths from the full spectrum. Pattern texture features (energy, contrast, homogeneity and entropy) were extracted from the gray-scale images at the effective wavelengths. The support vector machines (SVM) and partial least squares regression (PLSR) methods were used to establish classification and prediction models, respectively. The results showed that by using the combined data sets of effective wavelengths and texture features for modelling an optimal correct classification rate of 91.8%. could be achieved. The soil samples were first classified, then the local models were established for soil TN according to soil types, which achieved better prediction results than the general models. The overall results indicated that hyperspectral imaging technology could be used for soil type classification and soil TN determination, and data fusion combining spectral and image texture information showed advantages for the classification of soil types.

Determination and Visualization of Peimine and Peiminine Content in Fritillaria thunbergii Bulbi Treated by Sulfur Fumigation Using Hyperspectral Imaging with Chemometrics

Rapid, non-destructive, and accurate quantitative determination of the effective components in traditional Chinese medicine (TCM) is required by industries, planters, and regulators. In this study, near-infrared hyperspectral imaging was applied for determining the peimine and peiminine content in Fritillaria thunbergii bulbi under sulfur fumigation. Spectral data were extracted from the hyperspectral images. High-performance liquid chromatography (HPLC) was conducted to determine the reference peimine and peiminine content. The successive projection algorithm (SPA), weighted regression coefficient (Bw), competitive adaptive reweighted sampling (CARS), and random frog (RF) were used to select optimal wavelengths, while the partial least squares (PLS), least-square support vector machine (LS–SVM) and extreme learning machine (ELM) were used to build regression models. Regression models using the full spectra and optimal wavelengths obtained satisfactory results with the correlation coefficient of calibration (r_c), cross-validation (r_cv) and prediction (r_p) of most models being over 0.8. Prediction maps of peimine and peiminine content in Fritillaria thunbergii bulbi were formed by applying regression models to the hyperspectral images. The overall results indicated that hyperspectral imaging combined with regression models and optimal wavelength selection methods were effective in determining peimine and peiminine content in Fritillaria thunbergii bulbi, which will help in the development of an online detection system for real-world quality control of Fritillaria thunbergii bulbi under sulfur fumigation.