Machine Learning Facial Analysis: Face Recognition, Expression Recognition, and Gender Identification

Although humans are quite good at identifying known faces, we are not very skilled when we have to deal with a large number of unknown faces. On the other hand modern computers, with almost limitless memory and computational speed, could overcome these human limitations. One of the most successful applications of image analysis has been biometric face recognition technology; it has received significant attention, especially in the past several years due to a wide range of applications such as public surveillance and security, identity verification in the digital world, and modeling techniques in multimedia data management. Facial expression recognition is also important for targeted marketing, medical analysis, and human-robot interaction.

In this white paper, we review a few techniques for facial analysis – the cloud platform AWS Rekognition, deep learning, and traditional feature extraction algorithms. We show that to get high accuracy, good quality data and processing power are a must. We present the results of our experiments which have been conducted over six different public as well as proprietary image data sets.