A Semi-Automatic Method of Collecting Samples for Learning a Face Identification Algorithm

N. Yu. Bagrov, A. S. Konushin, V. S. Konushin

Abstract: A method for the semi-automatic collection of samples for learning face identification algorithms is proposed. In the experimental evaluation, the operation of the face identification algorithm on ethnically diverse data is considered. The algorithm operation is also evaluated on the data with a wide variation of ages. The proposed method makes it possible to expand the training sample by indexing new data.