Real-Time Face Recognition from Surveillance Video - Intelligent Video Event Analysis and Understanding - page 155

Real-Time Face Recognition from Surveillance
Video

Michael Davis, Stefan Popov, and Cristina Surlea

Abstract. This chapter describes an experimental system for the recognition of hu-
man faces from surveillance video. In surveillance applications, the system must be
robust to changes in illumination, scale, pose and expression. The system must also
be able to perform detection and recognition rapidly in real time.
Our system detects faces using the Viola-Jones face detector, then extracts local
features to build a shape-based feature vector. The feature vector is constructed from
ratios of lengths and differences in tangents of angles, so as to be robust to changes in
scale and rotations in-plane and out-of-plane. Consideration was given to improving
the performance and accuracy of both the detection and recognition steps.

1 Introduction

CCTV cameras have become ubiquitous, nowhere more so than in the United King-
dom. So far, the value of CCTV surveillance has failed to live up to the hype. A re-
cent report by the Metropolitan Police in London revealed that the city's one million-
plus cameras have helped to solve only a handful of crimes [18]. The criminologist
Clive Norris points out [21] that CCTV operators tend to act on their prejudices (for
example, focussing cameras on people because of their skin colour) or merely on
scenes which they find entertaining, to relieve the boredom of staring at mundane
street scenes all day. So far, the main CCTV success stories are for forensic use 1
and as a deterrent against some forms of petty or opportunistic crime 2 .