Approaching human level facial landmark localization by deep learning

作者:

Highlights:

• We show how to achieve state-of-the-art facial landmark localization by CNN.

• The system's performance is improved by deeper network.

• We show our system's performance is close to human.

摘要

•We show how to achieve state-of-the-art facial landmark localization by CNN.•The system's performance is improved by deeper network.•We show our system's performance is close to human.

论文关键词:Facial landmark localization,Deep learning,Convolutional neural network

论文评审过程:Received 3 March 2015, Revised 12 September 2015, Accepted 30 November 2015, Available online 12 December 2015, Version of Record 17 May 2016.

论文官网地址:https://doi.org/10.1016/j.imavis.2015.11.004