“…Multispectral imaging, as an emerging technology, combines imaging and spectroscopy techniques, which can not only provide spatial information of seeds such as area, perimeter, length, shape, color, etc., but also provide detailed information about chemical composition, structure and other internal characteristics, determining various traits of seeds simultaneously. The merits of non-destructive, easy and no sample pre-treatment make it widely applied to seed quality testing, such as identifying rice seeds ( Liu et al., 2016b ), classifying different tomato seed cultivars ( Shrestha et al., 2016 ), discriminating alfalfa cultivars seed ( Yang et al., 2020 ; Jia et al., 2022 ), classifying Jatropha curcas seed health ( Barboza da Silva et al., 2021 ). Sumathi and Balamurugan applied machine vision technology to identify the morphology of 11 oat cultivars, and the observation was more accurate and objective than manual method ( Sumathi and Balamurugan, 2013 ).…”