The agricultural production sector is of great interest to national economies, their GDP and the population's food chain. During digitalization and modernization, imaging techniques and machine learning are important driving factors. In this research, a narrative critical literature review was conducted on the most used imaging modalities and their use with machine learning methods, which are examined along with their applications in the agricultural industry in production activities, as well as their limitations and existing challenges. This research is intended to support a further development of a technological framework for intelligent precision agroindustry production. It was found that the most used imaging methods are hyperspectral and multispectral imaging, infrared thermal imaging, magnetic resonance imaging, X-ray imaging, scanning electron microscopy and ultraviolet imaging. The majority of employments of machine learning along with imaging was using supervised learning algorithms, there were a few applications using unsupervised and reinforcement learning algorithms. From the results and analysis, it can be concluded that the use of imaging techniques enables an increase in quality and profit maximization of agro-industrial products and their characterization data, which can be better analyzed with the help of machine learning methods and lead to a more sustainable and innovative agro-industrial productive sector.