Hyperspectral Imaging for Detection and Classification of Plant Primary and Secondary Metabolites: A Review

BACKGROUND: Hyperspectral imaging (HSI) is a nondestructive technique that simultaneously captures spectral and spatial information across multiple wavelengths. It has gained importance in plant science for detecting primary metabolites, vital for growth, and secondary metabolites, essential for plant defense and human health. Conventional methods such as chromatography and mass spectrometry, though accurate, are destructive, time-consuming, and require laborious sample preparation. OBJECTIVES: This review examines the potential of HSI as a rapid and noninvasive tool for metabolite detection and classification, emphasizing its role in precision agriculture, plant phenotyping, and medicinal plant research. METHODS: This review summarizes principles of HSI, hardware components, image acquisition strategies, and processing techniques. Special focus is given to the integration of machine learning for extracting and classifying biochemical information from high-dimensional spectral data. RESULTS: Studies show that HSI enables accurate, real-time assessment of plant metabolic profiles. Machine learning approaches enhance predictive performance, while advances in imaging sensors, illumination systems, and computational tools are improving applicability. HSI is increasingly adopted for monitoring plant quality, stress responses, and bioactive compound content. CONCLUSION: This review highlights HSI as a transformative tool in plant metabolomics, providing scalable, rapid, and sustainable alternatives to traditional methods, with strong potential to advance agricultural productivity and medicinal plant applications.