Enhanced face detection for biometric security
Abstract
Biometrics is an automated method of recognizing a person based on a physiological or behavioral
characteristic. Face recognition works by first obtaining an image of a person. This process is usually known
as face detection. In this paper we describe an algorithm for face detection that is able to locate a human face
embedded in a complicated background. Segmentation of novel or dynamic objects in a scene, often referred to as
background subtraction or foreground segmentation, is a critical early step in most computer vision applications
in domains such as surveillance and human-computer interaction. All previously implementations on, real-time
methods fail to handle properly one or more common phenomena, such as global illumination changes, shadows,
inter-reflections, similarity of foreground color to background, and non-static backgrounds (e.g. active video
displays or trees waving in the wind). The recent advent of hardware and software for real-time computation of
imagery makes better approaches possible. We propose a method for modeling the background that uses per-pixel,
time-adaptive, Gaussian mixtures in the combined input space of pixel neighborhood and luminance invariant color.
This combination in itself is novel. Our experiments show that the method possesses much greater robustness to
problematic phenomena than the prior state of the art methods, without sacrificing real-time performance, making
it well-suited for a wide range of practical applications in video events requiring detection and recognition.