Automated analysis of lettuce seed primary root protrusion using computer vision

Despite high germination rates in lettuce seeds, seedling emergence often varies in terms of the speed and percentage, highlighting the need for vigour assessments during the early stages of seedling development. This study employed transillumination imaging and machine learning (ML) to determine the optimal time intervals for assessing seed vigour in the Roxa and Vanda genotypes. Morphological parameters such as the area, perimeter, circularity, and solidity were extracted from the images using computer vision and analysed through multiple linear regressions applying the ordinary least squares (OLS) model. The results demonstrated that the proposed model effectively identified the morphological traits associated with seed vigour. By identifying the circularity and solidity as reliable early indicators of the physiological performance, the study established 21 hours for the Roxa genotype and 16 hours for the Vanda genotype as the most suitable evaluation periods, showing the strongest agreement with conventional vigour assessment methods. In particular, the circularity and solidity exhibited a strong association with the seed vigour and primary root protrusion dynamics. These findings highlight the potential of automated image processing and ML as rapid, objective and non-destructive tools for seed vigour assessments, contributing to significant advances in seed technology and quality assessment systems.