The multispectral imaging technique is considered a reformation of hyperspectral imaging. It can be employed to noninvasively and rapidly evaluate food quality. Even though several imaging or sensor‐based techniques have been conducted for the quality assessment of various food products, the rise of multispectral imaging has been more promising. This paper presents a comprehensive review of the use of the multispectral sensor in the quality assessment of plant foods (such as cereals, legumes, tubers, fruits, and vegetables). Different quality parameters (such as physicochemical and microbiological aspects) of plant‐based foods that were determined and visualized by the combination of modeling methods and feature wavelength selection approaches are summarized. Based on the literature, the most frequently used wavelength selection methods are the successive projection algorithm (SPA) and the regression coefficient (RC). The most effective models developed for analyzing plant food products are the partial least squares regression (PLSR), least square support vector machine (LS‐SVM), support vector machine (SVM), partial least squares discriminant analysis (PLSDA), and multiple linear regression (MLR). This article concludes with a discussion of challenges, potential uses, and future trends of this flourishing technique that is now also being applied to plant foods.

中文翻译：

---

用于植物食品质量分析和可视化的多光谱成像

多光谱成像技术被认为是高光谱成像的一种革新。它可用于无创快速评估食品质量。尽管已经进行了多种成像或基于传感器的技术来评估各种食品的质量，但多光谱成像的兴起却更具前景。本文对使用多光谱传感器对植物食品（例如谷物，豆类，块茎，水果和蔬菜）的质量评估进行了全面的综述。总结了通过建模方法和特征波长选择方法的组合确定和可视化的植物性食品的不同质量参数（例如理化和微生物学方面）。根据文献，最常用的波长选择方法是连续投影算法（SPA）和回归系数（RC）。用于分析植物食品的最有效模型是偏最小二乘回归（PLSR），最小二乘支持向量机（LS-SVM），支持向量机（SVM），偏最小二乘判别分析（PLSDA）和多重线性回归（MLR）。本文最后讨论了这种蓬勃发展的技术所面临的挑战，潜在用途和未来趋势，该技术目前也已应用于植物性食品。偏最小二乘判别分析（PLSDA）和多元线性回归（MLR）。本文最后讨论了这种蓬勃发展的技术所面临的挑战，潜在用途和未来趋势，该技术目前也已应用于植物性食品。偏最小二乘判别分析（PLSDA）和多元线性回归（MLR）。本文最后讨论了这种蓬勃发展的技术所面临的挑战，潜在用途和未来趋势，该技术目前也已应用于植物性食品。