数据采集与处理2016，Vol.31Issue(5)：996-1003,8.DOI:10.16337/j.1004-9037.2016.05.017
一种卷积神经网络和极限学习机相结合的人脸识别方法
Face Recognition Algorithm Based on Combination of Convolutional Neural Networks and Extreme Learning Machine
摘要
Abstract
Convolutional neural networks are good at learning features,but not always optimal for classifi-cation,while extreme learning machines are good at producing decision surfaces from well-behaved fea-ture vector,but cannot learn complicated invariances.Based on the advantages and disadvantages of con-volutional neural networks and extreme learning machine,we present a hybrid system where a convolu-tional neural network is trained to extract features and an extreme learning machine is trained from the features learned by the convolutional neural networks to recognize faces.We also propose prefix part of the filters in the convolutional layers to reduce parameters for improving the recognition accuracy.The experimental results obtained on the ORL and XM2VTS databases show that the proposed method can effectively improve the performance of face recognition,and the method of prefixing part of the filters is better than the method of stochastic filters in small training data.关键词
卷积神经网络/极限学习机/特征提取/人脸识别Key words
convolutional neural networks/extreme learning machine/feature extraction/face recogni-tion分类
信息技术与安全科学引用本文复制引用
余丹,吴小俊..一种卷积神经网络和极限学习机相结合的人脸识别方法[J].数据采集与处理,2016,31(5):996-1003,8.基金项目
国家自然科学基金(61373055)资助项目。 （61373055）
