Robust face alignment with cascaded coarse-to-fine auto-encoder network

In this paper, we present a novel face alignment method using a two-level cascaded auto-encoder networks (2-LCAN). In our framework, the first level auto-encoder networks generate rough facial landmarks locations by taking detected face images with low-resolution as inputs. The second level autoenco...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2017 IEEE International Conference on Image Processing (ICIP) s. 1477 - 1481
Hlavní autoři: Peng, Cheng, Ge, Yongxin, Hong, Mingjian, Huang, Sheng, Yang, Dan
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.09.2017
Témata:
Autoencoder Network
Coarse-to-Fine
Deep Learning
Face Alignment
Robustness
ISSN:2381-8549
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we present a novel face alignment method using a two-level cascaded auto-encoder networks (2-LCAN). In our framework, the first level auto-encoder networks generate rough facial landmarks locations by taking detected face images with low-resolution as inputs. The second level autoencoder networks are constructed by cascading several sub stacked auto-encoder networks (SSAN) in a coarse-to-fine manner. Each SSAN extracts SIFT features and local pixels features around current landmark positions, then fuses them together to further refine landmarks of different facial components with higher image resolutions. Finally, experimental results on LFPW and HELEN datasets demonstrate that our proposed method is significantly superior to the compared approaches both in accuracy and robustness.
ISSN:2381-8549
DOI:10.1109/ICIP.2017.8296527