Non-destructive assessment of apricot fruit quality by portable visible-near infrared spectroscopy

A Performance Evaluation of Two Hyperspectral Imaging Systems for the Prediction of Strawberries' Pomological Traits

Pomological traits are the major factors determining the quality and price of fresh fruits. This research was aimed to investigate the feasibility of using two hyperspectral imaging (HSI) systems in the wavelength regions comprising visible to near infrared (VisNIR) (400-1000 nm) and short-wave infrared (SWIR) (935-1720 nm) for predicting four strawberry quality attributes (firmness-FF, total soluble solid content-TSS, titratable acidity-TA, and dry matter-DM). Prediction models were developed based on artificial neural networks (ANN). The entire strawberry VisNIR reflectance spectra resulted in accurate predictions of TSS (R2 = 0.959), DM (R2 = 0.947), and TA (R2 = 0.877), whereas good prediction was observed for FF (R2 = 0.808). As for models from the SWIR system, good correlations were found between each of the physicochemical indices and the spectral information (R2 = 0.924 for DM; R2 = 0.898 for TSS; R2 = 0.953 for TA; R2 = 0.820 for FF). Finally, data fusion demonstrated a higher ability to predict fruit internal quality (R2 = 0.942 for DM; R2 = 0. 981 for TSS; R2 = 0.976 for TA; R2 = 0.951 for FF). The results confirmed the potential of these two HSI systems as a rapid and nondestructive tool for evaluating fruit quality and enhancing the product's marketability.

Nondestructive quality assessment and maturity classification of loquats based on hyperspectral imaging

The traditional method for assessing the quality and maturity of loquats has disadvantages such as destructive sampling and being time-consuming. In this study, hyperspectral imaging technology was used to nondestructively predict and visualise the colour, firmness, and soluble solids content (SSC) of loquats and discriminate maturity. On comparison of the performance of different feature variables selection methods and the calibration models, the results indicated that the multiple linear regression (MLR) models combined with the competitive adaptive reweighting algorithm (CARS) yielded the best prediction performance for loquat quality. Particularly, CARS-MLR models with optimal prediction performance were obtained for the colour (R2P = 0.96, RMSEP = 0.45, RPD = 5.38), firmness (R2P = 0.87, RMSEP = 0.23, RPD = 2.81), and SSC (R2P = 0.84, RMSEP = 0.51, RPD = 2.54). Subsequently, distribution maps of the colour, firmness, and SSC of loquats were obtained based on the optimal CARS-MLR models combined with pseudo-colour technology. Finally, on comparison of different classification models for loquat maturity, the partial least square discrimination analysis model demonstrated the best performance, with classification accuracies of 98.19% and 97.99% for calibration and prediction sets, respectively. This study demonstrated that the hyperspectral imaging technique is promising for loquat quality assessment and maturity classification.

Interactive Deep Learning for Shelf Life Prediction of Muskmelons Based on an Active Learning Approach

A pivotal topic in agriculture and food monitoring is the assessment of the quality and ripeness of agricultural products by using non-destructive testing techniques. Acoustic testing offers a rapid in situ analysis of the state of the agricultural good, obtaining global information of its interior. While deep learning (DL) methods have outperformed state-of-the-art benchmarks in various applications, the reason for lacking adaptation of DL algorithms such as convolutional neural networks (CNNs) can be traced back to its high data inefficiency and the absence of annotated data. Active learning is a framework that has been heavily used in machine learning when the labelled instances are scarce or cumbersome to obtain. This is specifically of interest when the DL algorithm is highly uncertain about the label of an instance. By allowing the human-in-the-loop for guidance, a continuous improvement of the DL algorithm based on a sample efficient manner can be obtained. This paper seeks to study the applicability of active learning when grading 'Galia' muskmelons based on its shelf life. We propose k-Determinantal Point Processes (k-DPP), which is a purely diversity-based method that allows to take influence on the exploration within the feature space based on the chosen subset k. While getting coequal results to uncertainty-based approaches when k is large, we simultaneously obtain a better exploration of the data distribution. While the implementation based on eigendecomposition takes up a runtime of O(n3), this can further be reduced to O(n·poly(k)) based on rejection sampling. We suggest the use of diversity-based acquisition when only a few labelled samples are available, allowing for better exploration while counteracting the disadvantage of missing the training objective in uncertainty-based methods following a greedy fashion.

Highly thermally stable Cr3+ and Yb3+ codoped Gd2GaSbO7 phosphors for broadband near-infrared applications

Gd₂GaSbO₇:Cr³⁺,Yb³⁺ phosphors with efficient broadband NIR emission were prepared by a solid-state reaction. Under the excitation of 448 nm, the Gd₂GaSbO₇:Cr³⁺ (GGS:Cr³⁺) phosphor exhibits a broadband NIR emission band centered at approximately 770 nm with a full width at half maximum (FWHM) of 160 nm. In addition, Yb³⁺ codoping can distinctly improve the photoluminescence properties of the GGS:Cr³⁺ phosphor, leading to broadening of the FWHM and greatly enhancing the thermal stability of the phosphor. Moreover, the energy conversion process of Cr³⁺ → Yb³⁺ ions was analyzed in detail, demonstrating that the energy transfer mechanism conformed to electric dipole-dipole interaction. The NIR pc-LEDs assembled with the GGS:Cr³⁺ phosphor and blue LED chips possessed a maximum NIR output power of ∼21 mW at 100 mA driving current, indicating promising applications of the synthesized phosphor in NIR pc-LEDs.

Application of near infra-red spectroscopy as an instantaneous and simultaneous prediction tool for anthocyanins and sugar in whole fresh raspberry

BACKGROUND

The determination of fresh whole raspberry quality is a laborious and expensive process for commercial producers and researchers. Quantitative results for raspberry quality parameters are currently determined using a range of chemical tests within a commercial laboratory. The present work is the first calibration and validation of near infra-red spectroscopy (NIRS) for instantaneous and simultaneous of prediction of raspberry quality parameters. The importance and applicability of the findings of this research underscore its need and importance for both producers and researchers.

RESULTS

Near infra-red quantification models were developed to predict the level of soluble solid concentration (SSC) and anthocyanins present in whole fresh raspberries. Results highlighted a promising application for the prediction of anthocyanins (R² _cv = 0.77) and SSC (R² _cv = 0.77). The anthocyanin model had an root mean square error (RMSE) of 12.57 mg/L whilst SSC had 0.76 °Brix.

CONCLUSION

Both NIR models combined with new portable NIR devices provide unprecedented opportunity for the application of instantaneous and simultaneous quality parameter prediction for commercial raspberry producers and researchers. The numerous benefits NIR has brought to other horticultural industries are now closer for the raspberry industry with this proof of concept. © 2020 Society of Chemical Industry.

Establishment of an Accurate Starch Content Analysis System for Fresh Cassava Roots Using Short-Wavelength Near Infrared Spectroscopy

Short-wavelength near infrared spectra in the interactance mode were collected from intact cassava roots and cassava flesh, using two portable spectrometers for the spectral regions of 720-1050 and 850-1150 nm, respectively. All starch prediction models were developed using the partial least squares regression. Good prediction performance was obtained from the cassava flesh (cross-section cut root) measurement with a correlation of prediction (r p) of 0.917 and standard error of prediction (SEP) of 1.73%, for both spectrometers. For the intact root, the prediction models were satisfactorily accurate with r p values of 0.687 and 0.772 and SEP of 3.151 and 2.803%, respectively. Moreover, the performance measurement of all optimum models was also evaluated according to ISO 12099:2017(E). The results showed that the predicted values were not significantly different from the actual values obtained from the standard method at 95% confidence intervals. These results showed the feasibility of using portable spectrometers to predict the starch content of fresh cassava roots.

Measuring Internal Maturity Parameters Contactless on Intact Table Grape Bunches Using NIR Spectroscopy

The determination of internal maturity parameters of table grape is usually done destructively using manual methods that are time-consuming. The possibility was investigated to determine whether key fruit attributes, namely, total soluble solids (TSS); titratable acidity (TA), TSS/TA, pH, and BrimA (TSS - k x TA) could be determined on intact table grape bunches using Fourier transform near-infrared (FT-NIR) spectroscopy and a contactless measurement mode. Partial Least Squares (PLS) regression models were developed for the maturity and sensory quality parameters using grapes obtained from two consecutive harvest seasons. Statistical indicators used to evaluate the models were the number of latent variables (LVs) used to build the model, the prediction correlation coefficient (R²p) and root mean square error of prediction (RMSEP). For the respective parameters TSS, TA, TSS/TA, pH, and BrimA, the LVs were 21, 23, 5, 7, and 24, the R²p = 0.71, 0.33, 0.57, 0.28, and 0.77, and the RMSEP = 1.52, 1.09, 7.83, 0.14, and 1.80. TSS performed best when moving smoothing windows (MSW) + multiplicative scatter correction (MSC) was used as spectral pre-processing technique, TA with standard normal variate (SNV), TSS/TA with Savitzky-Golay first derivative (SG1d), pH with SG1d, and BrimA with MSC. This study provides the first steps towards a completely nondestructive and contactless determination of internal maturity parameters of intact table grape bunches.

Shortwave Near-Infrared Spectroscopy for Rapid Detection of Aflatoxin B1 Contamination in Polished Rice

The objective of this research was to apply near-infrared spectroscopy, with a short-wavelength range of 950 to 1,650 nm, for the rapid detection of aflatoxin B₁ (AFB₁) contamination in polished rice samples. Spectra were obtained by reflection mode for 105 rice samples: 90 samples naturally contaminated with AFB₁ and 15 samples artificially contaminated with AFB₁. Quantitative calibration models to detect AFB₁ were developed using the original and pretreated absorbance spectra in conjunction with partial least squares regression with prediction testing and full cross-validation. The statistical model from the external validation process developed from the treated spectra (standard normal variate and detrending) was most accurate for prediction, with a correlation coefficient (r) of 0.952, a standard error of prediction of 3.362 μg/kg, and a bias of -0.778 μg/kg. The most predictive models according to full cross-validation were developed from the multiplicative scatter correction pretreated spectra (r = 0.967, root mean square error in cross-validation [RMSECV] = 2.689 μg/kg, bias = 0.015 μg/kg) and standard normal variate pretreated spectra (r = 0.966, RMSECV = 2.691 μg/kg, bias = 0.008 μg/kg). A classification-based partial least squares discriminant analysis model of AFB₁ contamination classified the samples with 90% accuracy. The results indicate that the near-infrared spectroscopy technique is potentially useful for screening polished rice samples for AFB₁ contamination.

Optimized Prediction of Reducing Sugars and Dry Matter of Potato Frying by FT-NIR Spectroscopy on Peeled Tubers

Dry matter content (DMC) and reducing sugars (glucose, fructose) contents of three potato varieties for frying (Innovator, Lady Claire, and Markies) were determined by applying Fourier-transform near-infrared spectrometry (FT-NIR), with paying particular attention to tubers preparation (unpeeled, peeled, and transversally cut tubers) before spectral acquisitions. Potatoes were subjected to normal storage temperature as it is processed in the industry (8 °C) and lower temperature inducing sugar accumulations (5 °C) for 195 and 48 days, respectively. Prediction of DMC has been successfully modeled for all varieties. A common model to the three varieties reached R², root mean square error (RMSEP), and ratio performance to deviation (RPD) values of 0.84, 1.2, and 2.49. Prediction accuracy of reducing sugars was variety dependent. Reducing sugars were accurately predicted for Innovator (R² = 0.84, RMSEP = 0.097, and RPD = 2.86) and Markies (R² = 0.78, RMSEP = 0.033, and RPD = 2.15) and slightly less accurate for Lady Claire (R² = 0.63, RMSEP = 0.036, and RPD = 1.64). The lack of accuracy obtained with the Lady Claire variety is mainly due to the tight variability in sugar content measured over the storage. Finally, the best preparation of the tuber from the point of view of the accuracy of the prediction models was to use the whole peeled potato. Such preparation allowed for the improvement in RPD values by 15% to 38% the RPD values depending on reducing sugars and 35% for DMC.

Advances in Non-Destructive Early Assessment of Fruit Ripeness towards Defining Optimal Time of Harvest and Yield Prediction-A Review

Global food security for the increasing world population not only requires increased sustainable production of food but a significant reduction in pre- and post-harvest waste. The timing of when a fruit is harvested is critical for reducing waste along the supply chain and increasing fruit quality for consumers. The early in-field assessment of fruit ripeness and prediction of the harvest date and yield by non-destructive technologies have the potential to revolutionize farming practices and enable the consumer to eat the tastiest and freshest fruit possible. A variety of non-destructive techniques have been applied to estimate the ripeness or maturity but not all of them are applicable for in situ (field or glasshouse) assessment. This review focuses on the non-destructive methods which are promising for, or have already been applied to, the pre-harvest in-field measurements including colorimetry, visible imaging, spectroscopy and spectroscopic imaging. Machine learning and regression models used in assessing ripeness are also discussed.

Qualitative and quantitative analysis of ochratoxin A contamination in green coffee beans using Fourier transform near infrared spectroscopy

BACKGROUND

Ochratoxin A (OTA) contamination is highly prevalent in a variety of agricultural products including the commercially important coffee bean. As such, rapid and accurate detection methods are considered necessary for the identification of OTA in green coffee beans. The goal of this research was to apply Fourier transform near infrared spectroscopy to detect and classify OTA contamination in green coffee beans in both a quantitative and qualitative manner.

RESULTS

PLSR models were generated using pretreated spectroscopic data to predict the OTA concentration. The best model displayed a correlation coefficient (r) of 0.814, a standard error of prediction (SEP and bias of 1.965 µg kg^-1 and 0.358 µg kg^-1 , respectively. Additionally, a PLS-DA model was also generated, displaying a classification accuracy of 96.83% for a non-OTA contaminated model and 80.95% for an OTA contaminated model, with an overall classification accuracy of 88.89%.

CONCLUSION

The results demonstrate that the developed model could be used for detecting OTA contamination in green coffee beans in either a quantitative or qualitative manner. © 2016 Society of Chemical Industry.

A Simplified, Light Emitting Diode (LED) Based, Modular System to be Used for the Rapid Evaluation of Fruit and Vegetable Quality: Development and Validation on Dye Solutions

NIR spectroscopy has proven to be one of the most efficient and ready to transfer tools to monitor product's quality. Portable VIS/NIR instruments are particularly versatile and suitable for field use to monitor the ripening process or quality parameters. The aim of this work is to develop and evaluate a new simplified optoelectronic system for potential measurements on fruit and vegetables directly in the field. The development, characterization and validation of an operative prototype is discussed. LED technology was chosen for the design, and spectral acquisition at four specific wavelengths (630, 690, 750 and 850 nm) was proposed. Nevertheless, attention was given to the modularity and versatility of the system. Indeed, the possibility to change the light sources module with other wavelengths allows one to adapt the use of the same device for different foreseeable applications and objectives, e.g., ripeness evaluation, detection of particular diseases and disorders, chemical and physical property prediction, shelf life analysis, as well as for different natures of products (berry, leaf or liquid). Validation tests on blue dye water solutions have shown the capability of the system of discriminating low levels of reflectance, with a repeatability characterized by a standard deviation proportional to the measured intensity and in general limited to 2%-4%.

Generalized assorted camera arrays: robust cross-channel registration and applications

One popular technique for multimodal imaging is generalized assorted pixels (GAP), where an assorted pixel array on the image sensor allows for multimodal capture. Unfortunately, GAP is limited in its applicability because of the need for multimodal filters that are amenable with semiconductor fabrication processes and results in a fixed multimodal imaging configuration. In this paper, we advocate for generalized assorted camera (GAC) arrays for multimodal imaging--i.e., a camera array with filters of different characteristics placed in front of each camera aperture. The GAC provides us with three distinct advantages over GAP: ease of implementation, flexible application-dependent imaging since filters are external and can be changed and depth information that can be used for enabling novel applications (e.g., postcapture refocusing). The primary challenge in GAC arrays is that since the different modalities are obtained from different viewpoints, there is a need for accurate and efficient cross-channel registration. Traditional approaches such as sum-of-squared differences, sum-of-absolute differences, and mutual information all result in multimodal registration errors. Here, we propose a robust cross-channel matching cost function, based on aligning normalized gradients, which allows us to compute cross-channel subpixel correspondences for scenes exhibiting nontrivial geometry. We highlight the promise of GAC arrays with our cross-channel normalized gradient cost for several applications such as low-light imaging, postcapture refocusing, skin perfusion imaging using color + near infrared, and hyperspectral imaging.

SPXY Sample Classification Method and Successive Projections Algorithm Combined with Near-Infrared Spectroscopy for the Determination of Total Sugar Content of Southern Xinjiang Jujube

Sugar degree is an important indicator of red jujube internal quality. The main objectives of this paper are to minimize the collinearity between spectral variables, to find the variable groups which containing the lowest redundant information,and establish the model with better robustness by means of fewer variables. This paper uses SPXY (sample set partitioning based on joint x-y distances) to divide calibrating samples,and applies successive projections algorithm (SPA) to select the near-infrared spectral characteristic variable of southern Xinjiang jujube total sugar. To further establish the partial least squares (PLS) model with selected variables. The root mean square error of prediction (RMSEP) of the model is 2.8804. The correlation coefficient of prediction r is 0.9005.To compare the established PLS model results between SPA selecting variables and full spectrum. The results showed that: Firstly, the divided calibrating samples is reasonable in SPXY way.Secondly, SPA optimizes 9 variables of the full spectrum 1557 variables,and prediction effect of the established PLS model is better than the full spectrum PLS model.Finally,SPA can effectively select characteristic wavelength of component under test.

A review on the applications of portable near-infrared spectrometers in the agro-food industry

Industry has created the need for a cost-effective and nondestructive quality-control analysis system. This requirement has increased interest in near-infrared (NIR) spectroscopy, leading to the development and marketing of handheld devices that enable new applications that can be implemented in situ. Portable NIR spectrometers are powerful instruments offering several advantages for nondestructive, online, or in situ analysis: small size, low cost, robustness, simplicity of analysis, sample user interface, portability, and ergonomic design. Several studies of on-site NIR applications are presented: characterization of internal and external parameters of fruits and vegetables; conservation state and fat content of meat and fish; distinguishing among and quality evaluation of beverages and dairy products; protein content of cereals; evaluation of grape ripeness in vineyards; and soil analysis. Chemometrics is an essential part of NIR spectroscopy manipulation because wavelength-dependent scattering effects, instrumental noise, ambient effects, and other sources of variability may complicate the spectra. As a consequence, it is difficult to assign specific absorption bands to specific functional groups. To achieve useful and meaningful results, multivariate statistical techniques (essentially involving regression techniques coupled with spectral preprocessing) are therefore required to extract the information hidden in the spectra. This work reviews the evolution of the use of portable near-infrared spectrometers in the agro-food industry.

Pear quality characteristics by Vis / NIR spectroscopy

Recently, non-destructive techniques such as the Vis / NIR spectroscopy have been used to evaluate the characteristics of maturation and quality of pears. The study aims to validate the readings by the Vis / NIR spectroscopy as a non-destructive way to assess the qualitative characteristics of pear cultivars 'Williams', 'Packams' and 'Carrick', produced according to Brazilian conditions. The experiment was conducted at the Pelotas Federal University, UFPel, in Pelotas / RS, and the instrument used to measure the fruit quality in a non-destructive way was the NIR- Case spectrophotometer (SACMI, Imola, Italy). To determine pears' soluble solids (SS) and pulp firmness (PF), it was established calibration equations for each variety studied, done from the evaluations obtained by a non-destructive method (NIR-Case) and a destructive method. Further on, it was tested the performance of these readings by linear regressions. The results were significant for the soluble solids parameter obtained by the Vis / NIR spectroscopy; however, it did not achieve satisfactory results for the pear pulp firmness of these cultivars. It is concluded that the Vis / NIR spectroscopy, using linear regression, allows providing reliable estimates of pears' quality levels, especially for soluble solids.

Multispectral vision for monitoring peach ripeness

The main objective of this research was to develop an automatic procedure able to classify Rich Lady commercial peaches according to their ripeness stage through multispectral imaging techniques. A classification procedure was applied to the ratio images calculated as red (R, 680 nm) divided by infrared (IR, 800 nm), that is, R/IR images. Four image-based ripeness reference classes (A: unripe to D: overripe) were generated from 380 fruit images (season 1: 2006) by a nonsupervised classification method and evaluated according to reference measurements of the ripeness of the same samples: Magness-Taylor penetrometry firmness, low-mass impact firmness, reflectance at 680 nm (R680, and soluble solids content. The assignment of unknown sample images from those season 1 images (internal validation, n = 380) and of 240 images from the 2nd season (season 2: 2007) to the ripeness reference classes (external validation) was carried out by computing the minimum Euclidean distance (classification distance, C(d)) between each unknown image histogram and the average histogram of each ripeness reference class. For both validation phases, firmness values decreased and R680 increased for increasing alphabetical order of image-based class letter, reflecting the ripening process. Moreover, 70% (season 1) and 80% (season 2) of the samples below bruise susceptibility firmness were classified into class D.

PRACTICAL APPLICATION

This work proposes and validates a procedure for assessing peach ripeness through spectral imaging. The control of ripeness in this fruit is crucial for ensuring its quality and the measurement of optimum peach ripeness at harvest and postharvest is a controversial issue, which needs to be balanced between a minimum ripeness, acceptable for the consumer, and a maximum ripeness, to minimize fruit losses during the postharvest process. The proposed method is nondestructive and quick, showing thus, a good perspective for its application in fresh fruit packing lines, either for peach ripeness assessment or for other fruits (providing adequate calibration).