N. Uozumi et al., APPLICATION OF IMAGE-ANALYSIS WITH NEURAL-NETWORK FOR PLANT SOMATIC EMBRYO CULTURE, Journal of fermentation and bioengineering, 76(6), 1993, pp. 505-509
A method of classifying celery embryos and nonembryos using image anal
ysis with a neural network to decide the time for transfer to the next
culture stage in plant somatic embryo culture is presented. Since the
image database of celery cells is vast, four key input parameters (ar
ea, ratio of length to width, circularity and distance dispersion) wer
e selected. Among these four parameters, use of the first three was fo
und to be satisfactory for classification between embryos and nonembry
os. Using the three parameters, the trained neural network was also ab
le to classify globular, heart- and torpedo-shaped embryos at a level
comparable with estimation by a human expert. By using the trained neu
ral network, the number of plantlets that would be formed after the se
cond regeneration culture of 14 d could be successfully predicted from
number of heart- and torpedo-shaped embryos at the end of the first r
egeneration stage.