Average Neural Face Embeddings for Gender Recognition

Abstract

In recent years, with the rise of artificial intelligence and deep learning, facial recognition technologies have been developed thatoperate with high accuracy even in adverse conditions. However, extracting demographic information such as gender, age and racefrom facial features has been a hot research area. In this study, a new Average Neural Face Embeddings (ANFE) method that usesfacial vectors of people for gender recognition is presented. Instead of training deep neural network from scratch, a simple, fast andeffective solution has been developed that performs a distance calculation between the average gender vectors and the person's facevector. The method proposed as a result of the study carried out provided a high and successful recognition performance with with96.47% of the males and 99.92% of the females.