Unconstrained Kinect video face database

Abstract

Unconstrained face recognition poses several challenges to existing algorithms and to address these variations, different methodologies are proposed, including utilizing video and 3D (depth) information. With the introduction of consumer level depth capturing devices such as Microsoft Kinect, research has been performed in utilizing low cost RGB-D depth data for characterizing and matching faces. Next generation of Kinect device, the Kinect version 2, has also been released which provides higher resolution color, depth and near infrared images at a comparable sensor cost. Such multiple information obtained from a single sensor can be extremely helpful in designing novel algorithms and systems for object and face recognition. This paper introduces the KaspAROV RGB-D video face database which contains face videos and images from both versions of the Kinect device for over 100 subjects which will be made available to the research community. The database captured in visible and NIR spectrum (along with depth) encompasses face images and videos with challenges such as pose, distance, and illumination. The database can be used to evaluate the performance of face recognition algorithms which utilize either uni-spectrum or multi-spectrum information. We provide standard experimental protocols for ease of comparative evaluation on the database and also include baseline results using several existing algorithms including a commercial face recognition system and deep learning algorithm.