Classification performance of the SVM with linear and rbf kernel, when the features are extracted from the penultimate layer of an AlexNet CNN trained with an www.image-net.org dataset.

Rows show the performance of each learning machine (SVM with linear kernel and SVM with rbf kernel) on each image view (head, dorsum and profile). Columns show accuracy, average precision and minimum precision performance for each label on top lists. H = head view; D = dorsal view; P = profile view; SVM-L = SVM with linear kernel; SVM-R = SVM with rbf kernel.