“…Taking this into account, robust algorithms, using artificial intelligence and machine learning, have been considered the future for quality operations, specially by integrating image analysis and processing with classical physiological measurements ( Deal et al., 2020 ; de Medeiros et al., 2020 ; Galletti et al., 2020 ; Ribeiro-Oliveira et al., 2020 ; Barboza da Silva et al., 2021 ; Batista et al., 2022 ; Oliveira et al., 2022 ). This, for example, can also be observed in platforms for phenotype analysis during the seed-seedling transition, such as SeedGerm ( Colmer et al., 2020 ), or ScreenSeed, a novel high throughput seed germination phenotyping method based on computer vision ( Merieux et al., 2021 ). It is possible to mention other examples of this technology transference such as the GERMINATOR, a high throughput scoring and curve fitting software for seed germination ( Joosen et al., 2010 ; Ligterink and Hilhorst, 2017 ), and the SeedStor, a publicly available database for the seed collections held by the Germplasm Resources Unit (GRU) ( Horler et al., 2018 ), It’s important to highlight that other phenotyping high throughput systems have been proposed over the years, including a chlorophyll fluorescence-based imaging (ChIF) system to detect emerging cotyledons ( Pavicic et al., 2019 ), and an automatic computer vision system using RGB image-based analysis to detect radicle emergence ( Ducournau et al., 2005 ).…”