Cascaded Regressions of Learning Features for Face Alignment
| Autor: | Sarra Ben Fredj, Ngoc-Trung Tran, Maurice Charbit, Fakhreddine Ababsa |
|---|---|
| Přispěvatelé: | Laboratoire Traitement et Communication de l'Information (LTCI), Télécom ParisTech-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Informatique, Biologie Intégrative et Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE), UFE, Observatoire de Paris, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL) |
| Jazyk: | angličtina |
| Rok vydání: | 2015 |
| Předmět: |
2d images
Restricted Boltzmann machine Training set Computer science Facial motion capture business.industry Face tracking Learning feature ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Synthetic data Regression [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing Face (geometry) Cascaded regression Computer vision Artificial intelligence State (computer science) business Face alignment |
| Zdroj: | 16th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2015) 16th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2015), Oct 2015, Catania, Italy. pp.705--716, ⟨10.1007/978-3-319-25903-1_61⟩ Advanced Concepts for Intelligent Vision Systems ISBN: 9783319259024 ACIVS |
| DOI: | 10.1007/978-3-319-25903-1_61⟩ |
| Popis: | International audience; Face alignment is a fundamental problem in computer vision to localize the landmarks of eyes, nose or mouth in 2D images. In this paper, our method for face alignment integrates three aspects not seen in previous approaches: First, learning local descriptors using Restricted Boltzmann Machine (RBM) to model the local appearance of each facial points independently. Second, proposing the coarse-to-fine regression to localize the landmarks after the estimation of the shape configuration via global regression. Third, and using synthetic data as training data to enable our approach to work better with the profile view, and to forego the need of increasing the number of annotations for training. Our results on challenging datasets compare favorably with state of the art results. The combination with the synthetic data allows our method yielding good results in profile alignment. That highlights the potential of using synthetic data for in-the-wild face alignment. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|