长沙理工大学学报（自然科学版）2017，Vol.14Issue(2)：85-91,7.
基于KL距离的卷积神经网络人脸特征提取模型
Face feature extraction model of convolutional neural network based on KL divergence
摘要
Abstract
In order to overcome the shortcomings of Euclidean distance measurement in face feature expression,a neural network face feature extraction model based on KL divergence is proposed.The convolution neural network is used to transform the input sample into a probability distribution.The distance between different samples is measured by the KL divergence,and a cost function is defined to optimize the distance.The back propagation algorithm is used to modify the parameters of convolution neural network,the network has a stronger ability to distinguish between facial features.The extracted face feature vector is transformed into neural network classifier to performs face validation with YouTube face database.The experimental results show that the method can not only improve the error rate but also improve the generalization performance.关键词
人脸识别/人脸验证/特征提取/KL距离/度量学习/卷积神经网络Key words
face recognition/face verification/feature extraction/KL divergence/metric learning/convolutional neural network分类
信息技术与安全科学引用本文复制引用
罗可,周安众..基于KL距离的卷积神经网络人脸特征提取模型[J].长沙理工大学学报（自然科学版）,2017,14(2):85-91,7.基金项目
国家自然科学基金资助项目(11671125,71371065) （11671125,71371065）
