Rapid Screen of the Color and Water Content of Fresh-Cut Potato Tuber Slices Using Hyperspectral Imaging Coupled with Multivariate Analysis

Abstract

Color index and water content are important indicators for evaluating the quality of fresh-cut potato tuber slices. In this study, hyperspectral imaging combined with multivariate analysis was used to detect the color parameters (L*, a*, b*, Browning index (BI), L*/b*) and water content of fresh-cut potato tuber slices. The successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were used to extract characteristic wavelengths, partial least squares (PLS) and least squares support vector machine (LS-SVM) were utilized to establish regression models. For color prediction, R2c, R2p and RPD of all the LSSVM models established for the five color indicators L*, a*, b*, BI, L*/b* were exceeding 0.90, 0.84 and 2.1, respectively. For water content prediction, R2c, R2p, and RPD of the LSSVM models were over 0.80, 0.77 and 1.9, respectively. LS-SVM model based on full spectra was used to reappear the spatial distribution of color and water content in fresh-cut potato tuber slices by pseudo-color imaging since it performed best in most cases. The results illustrated that hyperspectral imaging could be an effective method for color and water content prediction, which could provide solid theoretical basis for subsequent grading and processing of fresh-cut potato tuber slices.

Imaging Spectroscopy and Machine Learning for Intelligent Determination of Potato and Sweet Potato Quality

“…PLSR combined with feature wavelength selection methods such as selected interval partial least squares regression (iPLSR) yielded the R 2 P as high as 0.91 [ 85 , 91 ]. Then, the hyperspectral imaging was employed to measure the color index (L*, a*, b*, browning index (BI), L*/b*) of fresh-cut potato tuber slices [ 77 ]. Compared to PLSR, higher accuracies were obtained by using least squares support vector machine (LSSVM) and feature wavelength selection methods including SPA and CARS.…”

Application and interpretation of deep learning methods for the geographical origin identification of Radix Glycyrrhizae using hyperspectral imaging

“…Therefore, HSI can get both external characteristic information and internal molecular information of samples, providing the possibility for the comprehensive analysis of samples. In recent years, the quality assessment and variety classication of HSI in the elds of agriculture [14][15][16] and food [17][18][19][20][21][22] have attracted increasing attention. It is possible to rapidly and accurately identify the geographical origins of Radix Glycyrrhizae through HSI.…”

A study of starch content detection and the visualization of fresh-cut potato based on hyperspectral imaging

“…This model had an R c 2 value of 0.8514, RMSEC of 0.3259, R p 2 value of However, the research of the above scholars is aimed at the whole potato, not fresh-cut potato slices. One study by Xiao et al 29 reported the use of HSI for the prediction of water content in fresh-cut potatoes, and the optimal model was established on the full wavelengths, instead of characteristic wavelengths. At present, there is no report on starch content detection in fresh-cut potatoes.…”