In the previous installment of this series, the relationship between human being's evaluation and morphological features extracted from chrysanthemum cut flower was investigated in order to quantify the vague criteria that has been established based on human sense . It was also found that the individual morphological feature did not co-relate to human evaluation scores. It was considered that some combination of the features might improve the co-relation. The machine learning system such as the

more »

... neural networks was considered to be usefully to automate the cut flower evaluation process. In this paper, length of cut flower , stem diameter, leaf area, length between flower and top leaf, leaf length, and, stem bend were selected for input parameters of neural networks whose output parameter was a human evaluation score. The neural networks were trained by KNT (Kalman Neuro Training) method. From the results, it was observed that output value satisfactorily agreed the human evaluation score. The error was less than the human error resulted from the human double check procedure . It was also confirmed that the evaluation by the neural networks with several appropriate features was effective . In addition, a feasibility of automated cut flower evaluation system , which does not involve human error, was found.