Národní úložiště šedé literatury Nalezeno 2 záznamů.  Hledání trvalo 0.01 vteřin. 
Face Recognition in Security and Surveillance Camera Systems
Malach, Tobiáš ; Říha, Kamil (oponent) ; Hudec,, Róbert (oponent) ; Poměnková, Jitka (vedoucí práce)
The thesis deals with enhancing face recognition performance in surveillance CCTV systems and access control systems. This goal is achieved via optimization of face templates, which is a novel approach to recognition performance enhancement. The optimization of template creation results in templates which yield higher recognition performance. The face recognition performance investigation and its enhancement via optimized template creation requires meeting other partial goals which also are objectives of the thesis are as follows. The first one is the design and assembly of representative face database allowing to reach credible and confident face recognition results in surveillance CCTV and access control systems. The second objective is the methodology for statistically reliable comparison of results which enables us to reach relevant conclusions. The third is the template creation and its optimization. The achieved results show that template optimization enhances the recognition performance in the named challenging applications approximately by 4-8%, reaching even 15% in some cases. Optimization of template creation thus contributes to making the face recognition feasible in these applications.
Face Recognition in Security and Surveillance Camera Systems
Malach, Tobiáš ; Říha, Kamil (oponent) ; Hudec,, Róbert (oponent) ; Poměnková, Jitka (vedoucí práce)
The thesis deals with enhancing face recognition performance in surveillance CCTV systems and access control systems. This goal is achieved via optimization of face templates, which is a novel approach to recognition performance enhancement. The optimization of template creation results in templates which yield higher recognition performance. The face recognition performance investigation and its enhancement via optimized template creation requires meeting other partial goals which also are objectives of the thesis are as follows. The first one is the design and assembly of representative face database allowing to reach credible and confident face recognition results in surveillance CCTV and access control systems. The second objective is the methodology for statistically reliable comparison of results which enables us to reach relevant conclusions. The third is the template creation and its optimization. The achieved results show that template optimization enhances the recognition performance in the named challenging applications approximately by 4-8%, reaching even 15% in some cases. Optimization of template creation thus contributes to making the face recognition feasible in these applications.

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.