Non-Destructive Detection of Fruit Quality Parameters Using Hyperspectral Imaging, Multiple Regression Analysis and Artificial Intelligence

Spatial assessment of soluble solid contents on apple slices using hyperspectral imaging

The soluble solid content (SSC) is one of the important parameters depicting the quality, maturity and taste of fruits. This study explored hyperspectral imaging (HSI) and fluorescence spectral imaging (FSI) techniques, as well as suitable chemometric techniques to predict the SSC in kiwifruit. 90 kiwifruit samples were divided into 70 calibration sets and 20 prediction sets. The hyperspectral images of samples in the spectral range of 387 nm~1034 nm and the fluorescence spectral images in the spectral range of 400 nm~1000 nm were collected, and their regions of interest were extracted. Six spectral pre-processing techniques were used to pre-process the two spectral data, and the best pre-processing method was selected after comparing it with the predicted results. Then, five primary and three secondary feature extraction algorithms were used to extract feature variables from the pre-processed spectral data. Subsequently, three regression prediction models, i.e., the extreme learning machines (ELM), the partial least squares regression (PLSR) and the particle swarm optimization - least square support vector machine (PSO-LSSVM), were established. The prediction results were analyzed and compared further. MASS-Boss-ELM, based on fluorescence spectral imaging technique, exhibited the best prediction performance for the kiwifruit SSC, with the , and RPD of 0.8894, 0.9429 and 2.88, respectively. MASS-Boss-PLSR based on the hyperspectral imaging technique showed a slightly lower prediction performance, with the , , and RPD of 0.8717, 0.8747, and 2.89, respectively. The outcome presents that the two spectral imaging techniques are suitable for the non-destructive prediction of fruit quality. Among them, the FSI technology illustrates better prediction, providing technical support for the non-destructive detection of intrinsic fruit quality.

The performance of the apple cultivar ‘Golden Delicious’ was investigated in Northern Greece on five rootstocks: (i) seedling, (ii) (Malling) M 7, (iii) (Malling-Merton) MM 104, (iv) MM 106, and (v) MM 109. Trunk circumference was highest when scions of cv. ‘Golden Delicious’ were grafted on MM 109 rootstock and seedling. The highest photosynthetic rate was measured for scions grafted on seedling although it was not significantly different from that of MM 109. Flesh firmness, pH of juice, soluble solids content and titratable acidity at harvest and after storage of fruits for 4 months were not significantly different among the rootstocks. Production efficiency of cv. ‘Golden Delicious’ was higher when grafted on MM 106, intermediate on M7, MM 109 and MM 104, and lowest on seedling. Based on fruit weight and production efficiency measurements MM 106 and M 7 rootstocks were more appropriate for the region of Northern Greece.

Non-destructive and in-site estimation of apple quality and maturity by hyperspectral imaging

Ripeness evaluation of kiwifruit by hyperspectral imaging

Abstract. This article reports on using a Fourier series expansion method to extract features from hyperspectral scattering profiles for apple fruit firmness and soluble solids content (SSC) prediction. Hyperspectral scattering images of ‘Golden Delicious’ (GD), ‘Jonagold’ (JG), and ‘Delicious’ (RD) apples, harvested in 2009 and 2010, were acquired using an online hyperspectral imaging system over the wavelength region of 500 to 1000 nm. The moment method and Fourier series expansion method were used to analyze the scattering profiles of apples. The zeroth-first order moment (Z-FOM) spectra and Fourier coefficients were extracted from each apple, which were then used for developing fruit firmness and SSC prediction models using partial least squares (PLS) and least squares support vector machine (LSSVM). The PLS models based on the Fourier coefficients improved the standard errors of prediction (SEP) by 4.8% to 19.9% for firmness and by 2.4% to 13.5% for SSC, compared with the PLS models using the Z-FOM spectra. The LSSVM models for the prediction set of Fourier coefficients achieved better SEP results, with improvements of 4.4% to 11.3% for firmness and 2.8% to 16.5% for SSC over the LSSVM models for the Z-FOM spectra data and 3.7% to 12.6% for firmness and 5.4% to 8.6% for SSC over the PLS models for the Fourier coefficients. Experiments showed that Fourier series expansion provides a simple, fast, and effective means for improving Keywords: Apples, Firmness, Fourier series expansion, Hyperspectral scattering imaging, Least squares support vector machine, Partial least squares, Soluble solids content.

Visible/near-infrared (VNIR) spectroscopy and spectral scattering are based on different sensing principles, and they have shown different abilities for predicting apple fruit firmness and soluble solids content (SSC). Hence the two techniques could work synergistically to improve the quality prediction of apples. In this research, VNIR spectroscopic and spectral scattering data for the wavelength range of 4601,100 nm were collected for 6,631 apples of Delicious', 'Golden Delicious' and 'Jonagold' cultivars during the 2009 and 2010 harvest seasons and for three months after the refrigerated air storage. Partial least squares models were developed for each sensor and their combination to predict the fruit firmness and SSC for both single-year and cross-year data sets. The spectral scattering technique generally performed better in predicting firmness, whereas the VNIR technique was superior for prediction of SSC. Overall, the data fusion of the two sensors produced significant improvements (p<0.05) for prediction of the firmness and SSC than individual sensors. Cross-year prediction results for firmness and SSC were lower, compared with prediction results for each year. However, the cross-year prediction model for SSC was more robust and less sensitive to the harvest-year effect, compared to the firmness prediction model. Sensor fusion can provide more robust and accurate firmness and SSC assessment for apples.

Comparison of NIRS approach for prediction of internal quality traits in three fruit species

In-field and non-destructive monitoring of grapes maturity by hyperspectral imaging

IntroductionThe soluble solids content (SSC), titratable acidity (TA), and pH are key indicators for evaluating the quality of table grapes during storage. Conventional detection methods are typically destructive and time-consuming. To address this limitation, visible-near infrared (Vis-NIR) spectroscopy was employed in this study to enable rapid and non-destructive quality assessment of fresh table grapes throughout the storage period.MethodsSeedless White table grape samples were analyzed within the 200–1100 nm spectral range, and calibration models for key quality parameters (SSC, TA, and pH) were established. Three machine learning algorithms, partial least squares regression (PLSR), support vector machine (SVM), and extreme learning machine (ELM), were employed to develop spectral prediction models based on characteristic wavelengths selected using different feature extraction strategies, including the successive projection algorithm (SPA), uninformative variable elimination (UVE), and competitive adaptive reweighted sampling (CARS).ResultsThe results demonstrate that the SNV-CARS-SVM models achieved excellent performance in predicting SSC with a root mean square errors (RMSEP) of 0.673, a coefficient of determination for the prediction data set (Rp) of 0.928 and an RPD of 3.311. Similarly, the SNV-SPA-SVM models exhibited excellent predictive accuracy for TA, yielding an RMSEP of 0.553, an Rp of 0.873, and an RPD of 2.662. Good performances were achieved with Rp of 0.758 and RMSEP of 0.113 with the SNV-CARS-PLSR model for pH.DiscussionThis study, for the first time, utilized Vis-NIR spectroscopy to achieve the simultaneous and rapid determination of multiple quality attributes in table grapes, providing a novel and efficient strategy for real-time and non-destructive quality evaluation during storage. The proposed approach showed considerable potential for rapid quality assessment and postharvest management of grapes. Future research will focus on expanding the diversity of grape cultivars and investigating various storage conditions to improve the robustness and transferability of the predictive model, thereby promoting the industrial validation and practical application of Vis-NIR spectroscopy in fruit quality monitoring.

Blueberry is becoming increasingly popular because consumers like its flavor and antioxidant capacity for anti-aging. Firmness and soluble solids content (SSC) are the most important internal quality attributes for blueberries, and they are directly related to the maturity/ripeness and shelf life. The current blueberry firmness inspection systems are based on the mechanical vibration or impact principle, which could induce tissue damage, while computer vision systems only inspect external quality (i.e., size and color). This study reports on the prediction of firmness and SSC, using hyperspectral reflectance imaging in the region of 500-1,000 nm. A line scan system was used to acquire hyperspectral images of 300 blueberries for two fruit orientations (i.e., stem and calyx ends). Mean spectra were extracted from the regions of interest for the hyperspectral images of each blueberry. Prediction models were developed based on partial least squares method using cross validation and were externally tested with 25% of the samples. Better firmness predictions (R = 0.87) were obtained, compared to SSC predictions (R = 0.79). Fruit orientation had no or insignificant effect on firmness and SSC prediction. Further analysis showed that blueberries could be sorted into two classes of firmness. This research has demonstrated the feasibility of hyperspectral imaging technique for sorting and grading blueberries to enhance their quality and marketability.

Detection of mango soluble solid content using hyperspectral imaging technology

Hyperspectral imaging technology was used to assess the soluble solids content (SSC), titrable acidity content (TAC), and firmness of hami melons. The mean spectra were extracted from the regions of interest (ROI) of the hyperspectral images of each hami melon. Spectral data were first pretreated with different preprocessing methods and analyzed using the partial least squares (PLS) method to build calibration models. However, full spectral data contain a great number of redundant and colinear variables that lead to poor predicting ability of calibration models. Three typical variable selection methods, i.e., the genetic algorithm (GA), successive projections algorithm (SPA), and competitive adaptive reweighted sampling (CARS) were used to extract effective wavelength variables from the full spectra for determination of SSC, TAC, and firmness of hami melon. The results showed that the SNV‐CARS‐PLS model based on 51 and 40 wavelength variables achieved the optimal performance for SSC and TAC compared with full spectral SNV‐PLS, SNV‐GA‐PLS, and SNV‐SPA‐PLS models. The RP, RMSEP, and RPD of SNV‐CARS‐PLS model for SSC were 0.9606, 0.3816, and 3.598, respectively, and 0.9125, 0.0263, and 2.445 for TAC, respectively. The best model for predicting firmness was RAW‐CARS‐PLS model based on 57 wavelength variables with the RP RMSEP, and RDP values of 0.8671, 20.05, and 1.996, respectively. Overall, the results indicate that the CARS is a powerful method for selecting effective wavelength variables and demonstrated the feasibility of using hyperspectral imaging technology as a fast and nondestructive method for simultaneous detection of SSC, TAC, and firmness of hami melons.Practical applicationsThe quality of melon has a direct relationship with the soluble solids content, titrable acidity content, and texture of melon. To ensure the best taste and highest nutritional value, it is better for melons to be harvested when completely mature. Nowadays, melons were harvested according to different fruit development times after flowering. Traditional methods for detection of internal qualities and maturity of melon mainly focus on the appearance of melon and depend on the feelings of professionals, which are tedious, time‐consuming, expensive, and greatly influenced by subjective factors. More than anything, Traditional methods are hard to be highly accurate. Hyperspectral imaging technology has the advantages of rapid and nondestructive. The results showed that hyperspectral imaging technology for the simultaneous detection of soluble solids content, titrable acidity content, and firmness of melon is feasible. And the results can provide a reference for detecting large fruits by using hyperspectral imaging technology

Hyperspectral reflectance imaging technology in near-infrared regions (900–1,700 nm) was used to evaluate soluble solids content (SSC), firmness, moisture content (MC), and pH values of ‘Fuji’ apples during a 13-week storage period. Totally, 167 apples were divided into calibration set (125) and prediction set (42) based on the joint x-y distance sample set partitioning method. Mean spectrum of the regions of interest in the hyperspectral image of each apple was used for analysis. Two typical variable selection methods, i.e., successive projection algorithm (SPA) and uninformative variable elimination (UVE), were applied to extract the characteristic variables from full spectra (FS). The partial least squares (PLS) regression, least squares support vector machine (LSSVM), and backpropagation (BP) network modeling methods were used to establish models to predict SSC, firmness, MC, and pH of apples, respectively. The results showed that the SSC and MC could be predicted exactly by all developed models, and SPA-LSSVM and FS-BP could be used to predict pH value roughly. All models failed to predict firmness. The SPA-LSSVM model had better comprehensive ability in determining SSC, MC, and pH than others, with the correlation coefficient of prediction of 0.961, 0.984, and 0.882 and residual predictive deviation of 3.49, 5.51, and 2.06, respectively. The results demonstrated the feasibility of using near-infrared hyperspectral reflectance imaging technology as a non-invasive method for predicting SSC, MC, and pH of apples simultaneously.

Visible and near-infrared (VIS/NIR) spectroscopy has become a popular technique for non-invasive quality assessment of intact fruits. This work presents an application of a low-cost, commercially available NIR spectrometer for estimation of soluble solids content (SSC), titratable acidity (TA), and available acidity (pH) of 'Gannan' navel oranges (Citrus reticulata cv. orange). VIS/NIR spectra were acquired using a custom-designed, contact optical-fiber probe, and were recorded in transmission mode. Calibration models relating the VIS/NIR spectra to SSC, TA, and pH were developed based on two different regression methods, partial least square (PLS) regression and principal component regression (PCR), with respect to percent transmission (%T) spectra data and first- and second-derivative spectra. The prediction performance of the calibration models in different wavelength regions was also investigated. The best models were based on PLS regression methods, with root mean standard errors of validation (RMSEP) of 0.464 °Brix, 0.704 g L-1, and 0.125, and correlation coefficients (r2) of 0.804, 0.643, and 0.651 for SSC, TA, and pH, respectively. Based on the results, it can be concluded that VIS/NIR spectroscopy could be a reliable, accurate, and fast method for non-invasive measurements of navel orange SSC and acidity.