Output details
11 - Computer Science and Informatics
Manchester Metropolitan University
Article title
An evaluation of video-to-video face verification
Type
D - Journal article
Title of journal
IEEE Transactions on Information Forensics and Security
Article number
-
Volume number
5
Issue number
4
First page of article
781
ISSN of journal
1556-6021
Year of publication
2010
URL
-
Number of additional authors
13
Additional information
<23>This is a large study comparing performance of a range of video face recognition algorithms developed by different groups on a common, popular video data-set. The results show that the different algorithms obtain almost identical performance. This was demonstrated by comprehensive analysis of recognition rates. The significance of this work is that it shows that computational ease and efficiency are the overwhelming factors when selecting an algorithmic framework for the recognition of facial videos. The impact will be seen in the development of novel systems for recognising individuals.
Interdisciplinary
-
Cross-referral requested
-
Research group
A - Biological and Sensory Computation
Citation count
12
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
