摘要
为解决在人脸识别、表情识别等过程中,大规模姿态变化和遮挡等复杂环境下无法实现精确面部对齐的问题,提出一种深度回归网络(deep regression networks)下的人脸对齐方法。使用深度卷积神经网络对测试样本进行头部姿态估计并初始化人脸形状,降低头部姿态对人脸对齐造成的影响,在深度回归网络下进行局部回归微调,实现抗遮挡人脸精确对齐,使用图基的双权重函数作为训练深度回归网络的损失函数,减小训练过程中异常值的影响。选用300W和COFW人脸数据集进行测试,实验结果表明,该方法相比其它方法具有较强的鲁棒性,可实现大规模姿态变化和遮挡下人脸的精确对齐。
To solve face alignment in complex environment such as large-scale pose change and occlusion,in the process of face recognition and facial expression recognition,a face alignment method based on deep regression networks was put forward.The head pose of the test sample was estimated using deep convolutional neural networks and the facial shape was initialized,by which the effect of head pose on face alignment was reduced.Through the deep regression networks for local regression fine-tuning,anti-occlusion face accurate alignment was implemented.The Tukey＇s biweight function was used as the loss function of training deep regression networks,by which the influence of outliers in the training process was minimized.300 W and COFW face data sets were selected for testing.Experimental results show that the proposed method is more robust compared to other methods,and precise alignment of the face under large-scale pose change and occlusion was realized.
作者
冯文祥
文畅
谢凯
贺建飚
FENG Wen-xiang 1,WEN Chang 2 ,XIE Kai 1,HE Jian-biao 3(1.School of Electronic Information,Yangtze River University,Jingzhou 434023,China;2.School ofComputer Science,Yangtze River University,Jingzhou 434023,China;3.College of InformationScience and Engineering,Central South University,Changsha 410083,Chin)
出处
《计算机工程与设计》
北大核心
2018年第7期2069-2074,共6页
Computer Engineering and Design
基金
国家自然科学基金项目(61272147)
长江大学青年基金项目(2016cqn10)
长江大学大学生创新创业训练计划基金项目(2017009)
关键词
人脸对齐
卷积神经网络
人脸形状
头部姿态估计
局部微调
face alignment
convolutional neural networks
facial shape
head pose estimation
local fine tuning
