Kniha momentálne nie je na sklade
Parametre
Viac o knihe
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.
Nákup knihy
Video-to-Video Face Recognition for Low-Quality Surveillance Data, Christian Herrmann
- Jazyk
- Rok vydania
- 2018
Akonáhle sa objaví, pošleme vám e-mail.
Doručenie
Platobné metódy
Navrhnúť zmenu
- Titul
- Video-to-Video Face Recognition for Low-Quality Surveillance Data
- Jazyk
- anglicky
- Autori
- Christian Herrmann
- Vydavateľ
- KIT Scientific Publishing
- Vydavateľ
- 2018
- ISBN10
- 3731507994
- ISBN13
- 9783731507994
- Kategórie
- Počítače, IT, programovanie
- Anotácia
- 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.