“…With these extracted descriptors, supervised classification models such as support vector machine (SVM) [12, 13, 18, 19, 22–24, 27, 29, 31], subspace learning [10, 11, 14–16, 26], multiple instance learning [17, 25] and sparse representation [21, 32] are applied. However, the classification performance is often largely affected by the small number of training data available for bioimage research.…”