Prediction of soluble solids content and anthocyanin content in blood oranges based on hyperspectral reflectance and transmittance imaging technologies

To investigate the feasibility of hyperspectral imaging technique in nondestructive determination of soluble solids content (SSC) of fruits produced in different places and bagged with different materials during ripening, the near infrared hyperspectral reflectance images were acquired on 196 ‘Fuji’ apples picked from four orchards in different areas and bagged with polyethylene film or light-impermeable paper. Mean reflectance spectrum from the regions of interest in the hyperspectral image of each apple was extracted. Standard normal variate (SNV) was used to eliminate the effect of instrument and environment on spectra. The sample set partitioning based on joint x–y distances method was applied to divide the samples into calibration set and prediction set as the ratio of 3:1. Successive projection algorithm (SPA) and uninformative variable elimination (UVE) method were used to select effective wavelengths (EWs) from the full spectra. Partial least squares (PLS), least squares support vector machine (LSSVM), and extreme learning machine (ELM) were used to develop SSC determination models. The results showed that 24 and 122 EWs were selected by SPA and UVE, respectively. The selection of EWs was helpful to SSC determination performance improvement. The optimal SSC prediction model was LSSVM based on selected EWs by SPA, with the correlation coefficient and root-mean-square error of prediction set of 0.878 and 0.908 °Brix, respectively. This study indicates that hyperspectral imaging technique could be used to determine SSC of intact apples produced in different places and bagged with different materials during ripening.

The effect of fruit moving speed on online prediction of soluble solids content (SSC) of “Fuji” apples based on visible and near‐infrared (Vis/NIR) spectroscopy was studied. Diffuse transmission spectra between 615 and 1,045 nm were collected with a commercial online system at speeds of 0.3 m/s (S1), 0.5 m/s (S2), and 0.7 m/s (S3). Compensation models for SSC of each speed alone (local models) and all speeds (global model) were established using partial least squares (PLS). For global model, spectra of each sample were divided into three parts (P1, P2, and P3), three kinds of spectra partition combinations (P12, P13, and P23) were established. Results showed that S3 performed better and the influence of speed on spectra greatly affected SSC evaluation accuracy between local models. Comparatively, global model was insensitive to fruit moving speed variation and effective wavelengths (EWs) selected by competitive adaptive reweighted sampling (CARS) after Savitzky–Golay smoothing (SGS) achieved better results than local models. Importantly, 36 EWs selected by CARS after SGS of global‐P13 model achieved the best results with rp and RMSEP of 0.8419, 0.8895, 0.8948 and 0.6281, 0.5318, 0.5196°Brix, respectively. Generally, global‐P13 model with EWs is promisingly applied to online SSC prediction of apple by Vis/NIR diffuse transmission.Practical applicationsIt is of great value to study nondestructive and rapid methods for detecting apple SSC to meet the ever‐growing needs of consumers for continuous supply and high‐quality fruit. The methods and results in this study can provide basic references for Vis/NIR diffuse transmittance online detection of SSC of “Fuji” apple about fruit moving speed variation and model simplification. It is of great social value for developing a real‐time evaluation system of apple SSC in postharvest treatment or focusing on quality changing in storage shelf.

Effect of spectral measurement orientation on online prediction of soluble solids content of apple using Vis/NIR diffuse reflectance

Prediction of soluble solid content in Nanfeng mandarin by combining hyperspectral imaging and effective wavelength selection

Can light penetrate through pomelos and carry information for the non-destructive prediction of soluble solid content using Vis-NIRS?

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.

Optimization and comparison of models for prediction of soluble solids content in apple by online Vis/NIR transmission coupled with diameter correction method

Long-term evaluation of soluble solids content of apples with biological variability by using near-infrared spectroscopy and calibration transfer method

Nondestructive determining the soluble solids content of citrus using near infrared transmittance technology combined with the variable selection algorithm

Nondestructive measurement of soluble solids content in apple using near infrared hyperspectral imaging coupled with wavelength selection algorithm

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

Visible and near infrared (Vis-NIR) hyperspectral imaging was used for fast detection and visualization of soluble solid content (SSC) in ‘Beijing 553’ and ‘Red Banana’ sweet potatoes. Hyperspectral images were acquired from 420 ROIs of each cultivar of sliced sweet potatoes. There were 8 and 10 outliers removed from ‘Beijing 553’ and ‘Red Banana’ sweet potatoes by Monte Carlo partial least squares (MCPLS). The optimal spectral pretreatments were determined to enhance the performance of the prediction model. Successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were employed to select characteristic wavelengths. SSC prediction models were developed using partial least squares regression (PLSR), support vector regression (SVR) and multivariate linear regression (MLR). The more effective prediction performances emerged from the SPA–SVR model with Rp2 of 0.8581, RMSEP of 0.2951 and RPDp of 2.56 for ‘Beijing 553’ sweet potato, and the CARS–MLR model with Rp2 of 0.8153, RMSEP of 0.2744 and RPDp of 2.09 for ‘Red Banana’ sweet potato. Spatial distribution maps of SSC were obtained in a pixel-wise manner using SPA–SVR and CARS–MLR models for quantifying the SSC level in a simple way. The overall results illustrated that Vis-NIR hyperspectral imaging was a powerful tool for spatial prediction of SSC in sweet potatoes.

Multi-factor fusion models for soluble solid content detection in pear (Pyrus bretschneideri ‘Ya’) using Vis/NIR online half-transmittance technique

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

Effective wavelengths in visible-near infrared spectra region were selected based on successive projections algorithm (SPA). The selected effective wavelengths were set as inputs of least square support vector machine (LS-SVM) for qualitative analysis of soluble solid content (SSC) and firmness in pear. In this study, one-hundred and sixty samples were selected as sample set. 120 pear samples were selected randomly for the calibration set, and the remaining 40 samples for the prediction set. 16 variables included 431, 434, 439, 443, 448, 535, 595, 635, 681, 728, 742, 998, 1129, 1403, 1506 and 1771 nm, and 6 effective variables included 409, 412, 415, 419, 478 and 773 nm for prediction of SSC and firmness were selected by SPA for building the models of SSC and firmness, respectively. And, SPA-LS-SVM models were also compared with full-spectral PLS models, full-spectral LS-SVM models and SPA-PLS models. The correlation coefficients (r) of SSC and firmness were 0.8560 and 0.8452, respectively. The root mean square error of prediction (RMSEP) of SSC and firmness were 0.4648 and 1.0041, respectively. The overall results showed that SPA can fast and effectively select the optimal wavelengths. The selecting process is simple and does not need abundant parameter debugging. The prediction performance of SPA-LS-SVM model is better than conventional linear PLS model because SPA-LS-SVM model can enough use the linear and non-linear information in pear. In addition, this study also indicated that only visible spectra region or only NIR region was should not be considered for the prediction of SSC of pear because the color variances had certain indirect and latent relationship with the chemical compositions of pear. In terms of firmness prediction, it also indicated that visible light spectra may be more important for firmness prediction of pear.