Coarse-to-fine Face Alignment with Multi-Scale Local Patch Regression

2015/11/16 by Huang, Zhiao, Zhou, Erjin, Cao, Zhimin
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1511.04901

Abstract

Facial landmark localization plays an important role in face recognition and analysis applications. In this paper, we give a brief introduction to a coarse-to-fine pipeline with neural networks and sequential regression. First, a global convolutional network is applied to the holistic facial image to give an initial landmark prediction. A pyramid of multi-scale local image patches is then cropped to feed to a new network for each landmark to refine the prediction. As the refinement network outputs a more accurate position estimation than the input, such procedure could be repeated several times until the estimation converges. We evaluate our system on the 300-W dataset [11] and it outperforms the recent state-of-the-arts.

Related

• Facial Landmark Detection with Tweaked Convolutional Neural Networks
• Learning deep representation from coarse to fine for face alignment
• Effective face landmark localization via single deep network
• Deep Alignment Network: A convolutional neural network for robust face alignment
• Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learning