Fig. 6
From: Microalgae classification using semi-supervised and active learning based on Gaussian mixture models
Comparative of active learning metrics against a random selection using the first dataset, with results showing mean and standard deviation for the datasets with ten different bases. The vertical axis represents the accuracy and the horizontal axis represents the number of active samples informed to the system. a Accuracy for 1 % of initial semi-supervision, b MaxF1 for 1 % of initial semi-supervision, c accuracy for 10 % of initial semi-supervision, d MaxF1 for 10 % of initial semi-supervision, e accuracy for 50 % of initial semi-supervision, f MaxF1 for 50 % of initial semi-supervision (color figure online)