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...

Full description

Saved in:
Bibliographic Details
Published in:2017 IEEE International Conference on Image Processing (ICIP) pp. 1477 - 1481
Main Authors: Peng, Cheng, Ge, Yongxin, Hong, Mingjian, Huang, Sheng, Yang, Dan
Format: Conference Proceeding
Language:English
Published: IEEE 01.09.2017
Subjects:
Autoencoder Network
Coarse-to-Fine
Deep Learning
Face Alignment
Robustness
ISSN:2381-8549
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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