Varieties of biometric facial techniques for detecting offenders

Frowd, Charlie orcid iconORCID: 0000-0002-5082-1259 (2010) Varieties of biometric facial techniques for detecting offenders. Procedia Computer Science, 2 . pp. 3-10. ISSN 1877-0509

[thumbnail of Version of Record]
Preview
PDF (Version of Record) - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

1MB

Official URL: http://dx.doi.org/10.1016/j.procs.2010.11.002

Abstract

Many crimes are committed where the only record of the event is in the memory of a witness or victim. Recovering a recognisable image of the offender’s face is then crucial for solving the crime. Traditionally, eyewitnesses describe the offender’s face and select individual facial features – eyes, hair, nose, etc. – to build a ‘composite’. This image is then published in the media so that someone can recognise it and phone the police with a name. Unfortunately, when tested using life-like procedures, this method rarely produces recognisable images. The current paper describes these systems for extracting such biometric information from witnesses. It also describes how useful they are and explores three such approaches for improving their effectiveness. Included are a new method to interview witnesses (a holistic-cognitive interview), a new method to present images to the public (animated composite) and a new system to construct the face (EvoFIT).


Repository Staff Only: item control page