Abstract
Chemometrics methods coupled with hyperspectral imaging technology in visible and near infrared (Vis/NIR) region (380–1030 nm) were introduced to assess total soluble solids (TSS) in mulberries. Hyperspectral images of 310 mulberries were acquired by hyperspectral reflectance imaging system (512 bands) and their corresponding TSS contents were measured by a Brix meter. Random frog (RF) method was used to select important wavelengths from the full wavelengths. TSS values in mulberry fruits were predicted by partial least squares regression (PLSR) and least-square support vector machine (LS-SVM) models based on full wavelengths and the selected important wavelengths. The optimal PLSR model with 23 important wavelengths was employed to visualise the spatial distribution of TSS in tested samples, and TSS concentrations in mulberries were revealed through the TSS spatial distribution. The results declared that hyperspectral imaging is promising for determining the spatial distribution of TSS content in mulberry fruits, which provides a reference for detecting the internal quality of fruits.
Highlights
Hyperspectral imaging, as a tool for spectrochemical analysis, integrates the advantage of conventional imaging and spectroscopic technique, which can obtain both spatial and spectral information from a tested object and has been widely used in detecting quality of fruit products [1]
Hu et al [9] used a combination of Random frog (RF) selected reflectance and transmittance spectra from hyperspectral data to predict blueberry mechanical properties, and the results showed that prediction models based on RF had similar results with full spectral model
The successful mapping of total soluble solids (TSS) distribution in mulberries suggested that the application of hyperspectral imaging to realize the visualization of mulberry fruits’ internal quality is feasible and promising
Summary
Hyperspectral imaging, as a tool for spectrochemical analysis, integrates the advantage of conventional imaging and spectroscopic technique, which can obtain both spatial and spectral information from a tested object and has been widely used in detecting quality of fruit products [1]. Yu et al [4] implemented minimum noise fraction (MNF) rotation on important wavebands to extract the defective feature of hyperspectral images of loquat fruits and obtained that the identification accuracy was 92.3% Those methods only were used to eliminate useless information in view of spectra and neglect the relationship between spectral values and chemical concentrations. Selection of important wavelengths instead of full spectra of hyperspectral images has an advantage to generate chemical spatial distribution and provide a reference for developing portable multispectral imager [6]. It is Journal of Analytical Methods in Chemistry meaningful to extract important variables to establish robust calibration model
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
