An image acquisition system for automated monitoring of the germination rate of sunflower seeds

This paper presents a machine vision system designed to count the number of emergent radicle tips on seedlots, under controlled lighting, temperature and hygrometric conditions. The automated acquisition system employs an algorithm which works in two steps, in a totally unsupervised way. The first step consists of a classification procedure which makes it possible to transform colour images to binary images (seeds in white, background in black). In the second step, counting of the germinated seeds is performed, providing the mean germination time (MGT). The method was validated by comparing the results supplied by the system to those evaluated by expert technicians, on sets of sunflower seeds. (C) 2004 Elsevier B.V. All rights reserved.