Amaranth (Amaranthus caudatus L.) is an Andean pseudocereal with a nutritional profile characterized by its protein, dietary fiber, and bioactive compound content, adequate balance of essential amino acids, and the presence of bioactive compounds with antioxidant, anti-inflammatory, and cardiometabolic properties. This review analyzes the main processing methods applied to amaranth, including milling, roasting, popping, rolling, extrusion, germination, fermentation, encapsulation, and component isolation, describing how these technologies modify its nutritional, functional, and technological properties. It also examines its applications in various food categories, such as baked goods, extruded snacks, fermented beverages, symbiotic foods, and gluten-free formulations, highlighting its potential as a functional food ingredient for developing functional foods and nutraceuticals. Furthermore, this study discusses the technological and industrial challenges associated with its processing, including structural, sensory, and scalability limitations, within the context of the growing global demand for healthy and sustainable foods. Finally, the study identifies knowledge gaps and research priorities to optimize processing conditions, improve sensory acceptability, and enhance industrial value, thereby supporting further evaluation of its integration into food production systems.

This review examines three Andean pseudocereals: quinoa ( Chenopodium quinoa Willd.), kañiwa ( Chenopodium pallidicaule Aellen), and kiwicha ( Amaranthus caudatus L.). The focus is on the changes achieved through germination, enhanced by the use of emerging technologies applied as a pre-treatment. These grains are characterized by high-quality proteins with a complete essential amino acid profile, significant dietary fiber content, and diverse bioactive compounds with antioxidant, antihypertensive, and antidiabetic properties. This review covers conventional germination methods and parameters and explores emerging non-thermal technologies used as a pre-germination step. Although substantial research has investigated these technologies in quinoa, studies on kañiwa and kiwicha remain limited. Current evidence indicates that technologies such as ultrasound, high hydrostatic pressure, cold plasma, and magnetic fields can optimize enzymatic activity, reduce antinutrient content, and promote the synthesis of functional compounds. Gluten-free baked products made from germinated flour demonstrate improvements in rheological, textural, and sensory properties. However, challenges persist in defining industrial-scale parameters and addressing the high manufacturing costs of gluten-free products. A bibliometric analysis shows an increasing global interest in gluten-free products, creating commercial opportunities for these Andean pseudocereals. Kañiwa is identified as particularly promising due to its climatic resilience and nutritional value. The conclusion emphasizes the need for further research to optimize processing protocols and validate scaling approaches, thereby enhancing the contribution of pseudocereals to global food security and sustainable development.

Edible roots and tubers, such as potato, sweetpotato, cassava, and carrot, are vital to global food security; however, postharvest quality control still relies largely on costly, subjective manual inspection. Computer vision and machine learning applied to multiple imaging modalities have emerged as non-destructive approaches for automated inspection and quality assessment. This review synthesizes 141 studies (2016–2026) that applied these methods to the non-destructive quality assessment of edible roots and tubers. The reviewed studies span eight species, with potato (77.3%) and sweetpotato (17.0%) being dominant. RGB imaging is the most common acquisition modality (79%), alongside the growing use of hyperspectral and near-infrared spectroscopy. Deep learning is now the default approach, with its share rising from 18% (2016–2020) to 71% (2024–2026). YOLO-family detectors lead real-time sorting and defect detection, while classical image processing and machine learning remain competitive for narrowly defined tasks such as size grading. Several gaps stand out. Evidence beyond potato and sweetpotato remains thin. Public benchmarks are almost nonexistent, with only 5 of 141 studies using a public dataset. Foundation and zero-/few-shot models were almost absent from the reviewed studies, and most studies measure benchtop accuracy rather than the full inspection-to-actuation pipeline. This review maps where the field has matured and where it has not, offering a structured reference point and a research agenda for non-destructive quality evaluation of these crops.