Video-to-Video Face Recognition for Low-Quality Surveillance Data
The availability of video data is an opportunity and a challenge for law enforcement agencies. Face recognition methods can play a key role in the automated search for persons in the data. This work targets efficient representations of low-quality face sequences to enable fast and accurate face sear...
Saved in:
Main Author: | |
---|---|
Format: | Book Chapter |
Published: |
KIT Scientific Publishing
2018
|
Subjects: | |
Online Access: | Get Fullteks DOAB: description of the publication |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | The availability of video data is an opportunity and a challenge for law enforcement agencies. Face recognition methods can play a key role in the automated search for persons in the data. This work targets efficient representations of low-quality face sequences to enable fast and accurate face search. Novel concepts for multi-scale analysis, dataset augmentation, CNN loss function, and sequence description lead to improvements over state-of-the-art methods on surveillance video footage. |
---|---|
Physical Description: | 1 electronic resource (IX, 153 p. p.) |
ISBN: | KSP/1000083168 9783731507994 |
Access: | Open Access |