Extensive Facial Landmark Localization with Coarse-to-Fine Convolutional Network Cascade
Top Cited Papers
- 1 December 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 386-391
- https://doi.org/10.1109/iccvw.2013.58
Abstract
We present a new approach to localize extensive facial landmarks with a coarse-to-fine convolutional network cascade. Deep convolutional neural networks (DCNN) have been successfully utilized in facial landmark localization for two-fold advantages: 1) geometric constraints among facial points are implicitly utilized, 2) huge amount of training data can be leveraged. However, in the task of extensive facial landmark localization, a large number of facial landmarks (more than 50 points) are required to be located in a unified system, which poses great difficulty in the structure design and training process of traditional convolutional networks. In this paper, we design a four-level convolutional network cascade, which tackles the problem in a coarse-to-fine manner. In our system, each network level is trained to locally refine a subset of facial landmarks generated by previous network levels. In addition, each level predicts explicit geometric constraints (the position and rotation angles of a specific facial component) to rectify the inputs of the current network level. The combination of coarse-to-fine cascade and geometric refinement enables our system to locate extensive facial landmarks (68 points) accurately in the 300-W facial landmark localization challenge.Keywords
This publication has 6 references indexed in Scilit:
- Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face VerificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Face alignment by Explicit Shape RegressionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Localizing parts of faces using a consensus of exemplarsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Multi-PIEImage and Vision Computing, 2010
- Active appearance modelsIeee Transactions On Pattern Analysis and Machine Intelligence, 2001
- Active shape modelsPublished by Springer Science and Business Media LLC ,1998