Face recognition based on convolution neural network

In this paper, a face recognition method based on Convolution Neural Network (CNN) is presented. This network consists of three convolution layers, two pooling layers, two full-connected layers and one Softmax regression layer. Stochastic gradient descent algorithm is used to train the feature extra...

Full description

Saved in:
Bibliographic Details
Published inChinese Control Conference pp. 4077 - 4081
Main Authors Kewen Yan, Shaohui Huang, Yaoxian Song, Wei Liu, Neng Fan
Format Conference Proceeding
LanguageEnglish
Published Technical Committee on Control Theory, CAA 01.07.2017
Subjects
Caffe
CNN
Convolution
Face
Face recognition
Feature extraction
Image Processing
Neurons
Training
Online AccessGet full text

Cover

More Information
Summary:In this paper, a face recognition method based on Convolution Neural Network (CNN) is presented. This network consists of three convolution layers, two pooling layers, two full-connected layers and one Softmax regression layer. Stochastic gradient descent algorithm is used to train the feature extractor and the classifier, which can extract the facial features and classify them automatically. The Dropout method is used to solve the over-fitting problem. The Convolution Architecture For Feature Extraction framework (Caffe) is used during the training and testing process. The face recognition rate of the ORL face database and AR face database based on this network is 99.82% and 99.78%.
ISSN:1934-1768
DOI:10.23919/ChiCC.2017.8027997