Imputing Human Descriptions in Semantic Biometrics


Reid, Daniel and Nixon, Mark (2010) Imputing Human Descriptions in Semantic Biometrics. At Multimedia in Forensics, Security and Intelligence

Download

[img] PDF - Published Version
Download (724Kb)

Description/Abstract

Human identification at a distance has received significant interest due to the ever increasing surveillance infrastructure. Biometrics such as face and gait offer a suitable physical attribute to uniquely identify people from a distance. When linking this with human perception, these biometrics suffer from the semantic gap which is the difference between how people and how biometrics represent and describe humans. Semantic biometrics bridges this gap, allowing conversions between gait biometrics and semantic descriptions. One possible application of semantic biometrics is to automatically search surveillance footage for a person who best matches a given semantic description - possibly obtained from an eyewitness report. We now exploit patterns and structure within the physical descriptions to be able to predict occluded or erroneous data, thereby widening application potential. We show how imputation techniques can be used to increase accuracy and robustness of automatic semantic annotation of gait signatures.

Item Type: Conference or Workshop Item (Speech)
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Comms, Signal Processing & Control
ePrint ID: 271623
Date Deposited: 13 Oct 2010 12:54
Last Modified: 27 Mar 2014 20:17
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/271623

Actions (login required)

View Item View Item