3D Face Registration: Using Multiple Average Models - Ne?e Alyüz - Bøger - LAP Lambert Academic Publishing - 9783838318141 - 2. juni 2010
Ved uoverensstemmelse mellem cover og titel gælder titel

3D Face Registration: Using Multiple Average Models

Ne?e Alyüz

Pris
DKK 491

Bestilles fra fjernlager

Forventes klar til forsendelse 19. - 29. apr.
Tilføj til din iMusic ønskeseddel
Eller

3D Face Registration: Using Multiple Average Models

Three dimensional (3D) face recognition is a frequently used biometric and its performance is dependent on registration. Registration aligns two faces and makes a comparison possible between the two surfaces. In the literature, best results have been achieved by a one-to-all approach, where a test face is aligned to each gallery face separately. To overcome the computational bottleneck of this approach, we examine registration based on an Average Face Model (AFM). To improve the registration, we propose to group faces and register with category-specific AFMs. We see that gender and morphology classes exist, when faces are categorized with the clustering approach. As another factor causing diversity in the face space, we explore expression variations. To reduce the negative effect of expressions in registration, we divide the facial surface into logical segments, and for each segment we create an Average Region Model (ARM). Registering via each ARM separately, we examine regional recognition performance. Even though some regions are less affected by expression variations, no single region is sufficient by itself and the use of all regions is beneficial.

Medie Bøger     Paperback Bog   (Bog med blødt omslag og limet ryg)
Udgivet 2. juni 2010
ISBN13 9783838318141
Forlag LAP Lambert Academic Publishing
Antal sider 88
Mål 225 × 5 × 150 mm   ·   140 g
Sprog Engelsk