Computer Vision as a Complementary Method to Vigour Analysis in Maize Seeds

Abstract

Rapid and accurate evaluation of seed lot physiological potential is strongly desirable for the success of quality control programs conducted by seed industry. This study aims to evaluate the efficiency of computer vision through a free software of processing seedling digital images, in order to characterise maize seeds physiological potential and make comparisons among routine vigour tests, recommended for this species. So that, germination test, first germination count, seedling emergence, cold test, germination speed index and electrical conductivity test were used for featuring the physiological potential of maize seed lots. Then, these tests' results were compared with data collected, using an image analysis technique, through SAPL® software. Seedlings growth were evaluated by photographs on the seventh day and obtained the values of the primary root, coleoptile, and whole seedlings length, as well as growth, uniformity, vigour and corrected vigour indices. The computerised images analysis of seedlings through SAPL® is a consistent and promising alternative for evaluating the physiological potential of maize seeds. Its efficiency was proved in this study, being equivalent to what verified in routine tests for vigour determination.