ABSTRACT Cereal quality significantly influences human health, requiring thorough evaluation of authenticity, nutritional composition, and food safety hazards. Conventional detection methods are often characterized by limitations, including time‐consuming intricacy, complexity, and limited sensitivity. Recently, optical imaging and spectroscopy have emerged as rapid, nondestructive, and high‐throughput alternatives for assessing cereal quality. The integration of chemometrics and artificial intelligence (AI), particularly deep learning algorithms, is paramount in the processing and analysis of optical data, which is indispensable for extracting key features from large datasets. In this work, the advanced spectroscopy and optical imaging techniques are comprehensively introduced, and their recent progress in applied research is outlined, emphasizing the major innovations and practical applications of these techniques. Besides, the latest developments of these techniques and AI‐driven data processing methods in various aspects of cereal quality assessment have been summarized in order to highlight the potential research directions and future trends for practical application.
Li et al. (2025) studied this question.