Abstract
The task of forensic facial experts is to assess the likelihood whether a suspect is depicted on crime scene images. They typically (a) use morphological analysis when comparing parts of the facial region, and (b) combine this partial evidence into a final judgment. Facial parts can be considered as soft biometric modalities and in recent years have been studied in the biometric community. In this paper we focus on the region around the eye from a forensic perspective by applying the FISWG feature list of the eye modality. We compare existing work from the soft biometric perspective based on a texture descriptor with our approach.
Original language | Undefined |
---|---|
Title of host publication | 23rd European Signal Processing Conference, EUSIPCO 2015 |
Publisher | IEEE |
Pages | 779-783 |
Number of pages | 5 |
ISBN (Print) | 978-0-9928626-3-3 |
Publication status | Published - Sept 2015 |
Event | 23rd European Signal Processing Conference, EUSIPCO 2015 - Nice, France Duration: 31 Aug 2015 → 4 Sept 2015 Conference number: 23 http://www.eusipco2015.org/ |
Publication series
Name | |
---|---|
Publisher | IEEE Signal Processing Society |
Conference
Conference | 23rd European Signal Processing Conference, EUSIPCO 2015 |
---|---|
Abbreviated title | EUSIPCO |
Country/Territory | France |
City | Nice |
Period | 31/08/15 → 4/09/15 |
Internet address |
Keywords
- SCS-Safety
- EWI-26479
- FISWG
- METIS-315040
- IR-98378
- Forensic Facial Recognition
- eye modality