Facial Feature Extraction Method Based on Fast and Effective Convolutional Neural Network

摘要：

　　It is difficult for shallow networks to extract effective facial features,while it is time-consuming using deep networks with many iterations.This paper proposes a facial feature extraction method based on Fast and Effective Convolutional Neural Network(FECNN).Firstly,a deep network based on NIN method is presented to extract effective facial features.Then,a new Inception structure is used to deepen and widen the network while reducing the number of parameters.Finally,this network is embedded with Batch Normalization(BN)algorithm which greatly accelerates network convergence.Experimental results indicate that FECNN converges efficiently and robust facial features are extracted with less parameters.

关键词： facial feature extraction NIN Inception Batch Normalization FECNN

作者: Lu Lv Xiaodong Cai Yan Zeng Chaochun Chen

作者单位: School of Information and Communication,Guilin University of Electronic Technology,China School of Information and Communication,Guilin University of Electronic Technology,China;Internet of

会议类型: 国际会议

会议名称: 2017 IEEE 2nd Advanced Information Technology,Electronic and Automation Control Conference(IAEAC 2017)(2017 IEEE 第2届先进信息技术、电子与自动化控制国际会议)

会议地点: 重庆

会议语种:英文

页码: 2011-2015

在线出版日期: 2017-03-25（万方平台首次上网日期，不代表论文的发表时间）