Conformal mapping-based 3D face recognition
| Autor: | Szeptycki, Przemyslaw, Ardabilian, Mohsen, Chen, Liming, Zeng, Wei, Gu, David, Samaras, Dimitris |
|---|---|
| Přispěvatelé: | Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Université Lumière - Lyon 2 (UL2), SI LIRIS, Équipe gestionnaire des publications |
| Jazyk: | angličtina |
| Rok vydání: | 2010 |
| Předmět: | |
| Zdroj: | 3DPVT 2010-Fifth International Symposium on 3D Data Processing, Visualization and Transmission 3DPVT 2010-Fifth International Symposium on 3D Data Processing, Visualization and Transmission, May 2010, Paris, France. pp.1-8 |
| Popis: | International audience; In this paper we present a conformal mapping-based approachfor 3D face recognition. The proposed approachmakes use of conformal UV parameterization for mappingpurpose and Shape Index decomposition for similarity measurement.Indeed, according to conformal geometry theory,each 3D surface with disk topology can be mapped ontoa 2D domain through a global optimization, resulting in adiffeomorphism, i.e., one-to-one and onto. This allows usto reduce the 3D surface matching problem to a 2D imagematching one by comparing the corresponding 2D conformalgeometric maps. To deal with facial expressions, theM¨obius transformation of UV conformal space has beenused to ’compress’ face mimic region. Rasterized imagesare used as an input for (2D)2PCA recognition algorithm.Experimented on 62 subjects randomly selected from theFRGC dataset v2 which includes different facial expressions,the proposed method displays a 86.43%, 97.65% and69.38 rank-one recognition rate in respectively Neutral vs.All, Neutral vs. Neutral and Neutral vs. Expression scenarios. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|