Fourier transform infrared (FT‐IR) and Raman and hyperspectral imaging (HSI) techniques have emerged as reliable analytical methods for effectively characterizing and quantifying quality attributes of different categories of powdery food products (such as milk powder, tea powder, cocoa powder, coffee powder, soybean flour, wheat flour, and chili powder). In addition to the ability for gaining rapid information about food chemical components (such as moisture, protein, and starch), and classifying food quality into different grades, such techniques have also been implemented to determine trace impurities in pure foods and other properties of particulate foods and ingredients with avoidance of extensive sample preparation. Developments of corresponding quality evaluation systems based on FT‐IR, Raman, and HSI data that measure food quality parameters and ensure product authentication, would bring about technical and economic benefits to the food industry by enhancing consumer confidence in the quality of its products. Accordingly, a comprehensive review of the mushrooming spectroscopy‐based FT‐IR, Raman, and HSI literature is carried out in this article. The spectral data collected, the chemometric methods used, and the main findings of recent research studies on quality assessments of powdered materials are discussed and summarized. Providing a review in such a flourishing research field is relevant as a signpost for future study. The conclusion details the promise of how such noninvasive and powerful analytical techniques can be used for rapid and accurate determinations of powder quality attributes in both academical and industrial settings.

Staple foods, including cereals, legumes, and root/tuber crops, dominate the daily diet of humans by providing valuable proteins, starch, oils, minerals, and vitamins. Quality evaluation of staple foods is primarily carried out on sensory (e.g. external defect, color), adulteration (e.g. species, origin), chemical (e.g. starch, proteins), mycotoxin (e.g. Fusarium toxin, aflatoxin), parasitic infection (e.g. weevil, beetle), and internal physiological (e.g. hollow heart, black heart) aspects. Conventional methods for the quality assessment of staple foods are always laborious, destructive, and time-consuming. Requirements for online monitoring of staple foods have been proposed to encourage the development of rapid, reagentless, and noninvasive techniques. Spectroscopic techniques, such as visible–infrared spectroscopy, Raman spectroscopy, nuclear magnetic resonance spectroscopy, and spectral imaging, have been introduced as promising analytical tools and applied for the quality evaluation of staple foods. This review summarizes the recent applications and progress of such spectroscopic techniques in determining various qualities of staple foods. Besides, challenges and future trends of these spectroscopic techniques are also presented.

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.

Crop productivity is readily reduced by competition from weeds. It is particularly important to control weeds early to prevent yield losses. Limited herbicide choices and increasing costs of weed management are threatening the profitability of crops. Smart agriculture can use intelligent technology to accurately measure the distribution of weeds in the field and perform weed control tasks in selected areas, which cannot only improve the effectiveness of pesticides, but also increase the economic benefits of agricultural products. The most important thing for an automatic system to remove weeds within crop rows is to utilize reliable sensing technology to achieve accurate differentiation of weeds and crops at specific locations in the field. In recent years, there have been many significant achievements involving the differentiation of crops and weeds. These studies are related to the development of rapid and non-destructive sensors, as well as the analysis methods for the data obtained. This paper presents a review of the use of three sensing methods including spectroscopy, color imaging, and hyperspectral imaging in the discrimination of crops and weeds. Several algorithms of machine learning have been employed for data analysis such as convolutional neural network (CNN), artificial neural network (ANN), and support vector machine (SVM). Successful applications include the weed detection in grain crops (such as maize, wheat, and soybean), vegetable crops (such as tomato, lettuce, and radish), and fiber crops (such as cotton) with unsupervised or supervised learning. This review gives a brief introduction into proposed sensing and machine learning methods, then provides an overview of instructive examples of these techniques for weed/crop discrimination. The discussion describes the recent progress made in the development of automated technology for accurate plant identification as well as the challenges and future prospects. It is believed that this review is of great significance to those who study automatic plant care in crops using intelligent technology.

In many regions of the world, wheat is vulnerable to severe yield and quality losses from the fungus disease of Fusarium head blight (FHB). The development of resistant cultivars is one means of ameliorating the devastating effects of this disease, but the breeding process requires the evaluation of hundreds of lines each year for reaction to the disease. These field evaluations are laborious, expensive, time-consuming, and are prone to rater error. A phenotyping cart that can quickly capture images of the spikes of wheat lines and their level of FHB infection would greatly benefit wheat breeding programs. In this study, mask region convolutional neural network (Mask-RCNN) allowed for reliable identification of the symptom location and the disease severity of wheat spikes. Within a wheat line planted in the field, color images of individual wheat spikes and their corresponding diseased areas were labeled and segmented into sub-images. Images with annotated spikes and sub-images of individual spikes with labeled diseased areas were used as ground truth data to train Mask-RCNN models for automatic image segmentation of wheat spikes and FHB diseased areas, respectively. The feature pyramid network (FPN) based on ResNet-101 network was used as the backbone of Mask-RCNN for constructing the feature pyramid and extracting features. After generating mask images of wheat spikes from full-size images, Mask-RCNN was performed to predict diseased areas on each individual spike. This protocol enabled the rapid recognition of wheat spikes and diseased areas with the detection rates of 77.76% and 98.81%, respectively. The prediction accuracy of 77.19% was achieved by calculating the ratio of the wheat FHB severity value of prediction over ground truth. This study demonstrates the feasibility of rapidly determining levels of FHB in wheat spikes, which will greatly facilitate the breeding of resistant cultivars.