A coarse-to-fine curvature analysis-based rotation invariant 3D face landmarking
| Autor: | Przemyslaw Szeptycki, Mohsen Ardabilian, Liming Chen |
|---|---|
| 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), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-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) |
| Jazyk: | angličtina |
| Rok vydání: | 2009 |
| Předmět: |
Ground truth
Face hallucination Computer science business.industry Feature extraction Image registration 020206 networking & telecommunications Pattern recognition 02 engineering and technology Facial recognition system Gesture recognition 0202 electrical engineering electronic engineering information engineering Three-dimensional face recognition 020201 artificial intelligence & image processing Computer vision [INFO]Computer Science [cs] Artificial intelligence Invariant (mathematics) business |
| Zdroj: | International Conference on Biometrics: Theory, Applications and Systems International Conference on Biometrics: Theory, Applications and Systems, Sep 2009, Washington, United States. pp.1-6, ⟨10.1109/BTAS.2009.5339052⟩ |
| DOI: | 10.1109/BTAS.2009.5339052⟩ |
| Popis: | International audience; Automatic 2.5D face landmarking aims at locatingfacial feature points on 2.5D face models, such as eye corners,nose tip, etc. and has many applications ranging from faceregistration to facial expression recognition. In this paper, wepropose a rotation invariant 2.5D face landmarking solutionbased on facial curvature analysis combined with a generic2.5D face model and make use of a coarse-to-fine strategy formore accurate facial feature points localization. Experimentedon more than 1600 face models randomly selected from theFRGC dataset, our technique displays, compared to a groundtruth from a manual 3D face landmarking, a 100% of good nosetip localization in 8 mm precision and 100% of good localizationfor the eye inner corner in 12 mm precision. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|