Food crops are highly susceptible to contamination with toxigenic fungi before and after harvest. This can be due to environmental factors or poor logistics during handling, processing and storage. Usually, biological approaches are used to identify and quantify fungi, while chemical analysis does the same for the metabolites of the fungi, mycotoxins. These approaches are time-consuming, skill-demanding, expensive and susceptible to sampling technique. Hyperspectral imaging (HSI) is a proven alternative among the emerging technologies as its deployment at any stage in the food production system is easy and rapid. This is a unique review wherein the HSI applications for rapid and non-destructive estimation and quantification of mycotoxin contamination studies and research findings in different food crops including cereals, pulses, oilseeds, fruits, nuts and dried fruits have been grouped and discussed systematically. This chapter presents different hypercube pre-processing techniques, traditional chemometrics in relation to machine learning approaches are also enumerated in relation to the groundwork for new HSI conceptual frameworks, exposes research inconsistencies, synthesizes diverse findings and provides other researchers with an overview of subject.