A Convolutional Neural Network Face Recognition Algorithm Based on Data Augmentation
Abstract:
Aiming at the problems of light changing and face blurring in face recognition based on convolution neural network,an optimization algorithm of data augmentationt is proposed, which uses LeNet and adds pool layer structure to extract face features.After the ORL database is enhanced, the training set and the test set are randomly generated for expeimental verification. The experimental results show that the accuracy of face recognition can reach 100% on the test set, and it has good robustness for some degree of illumination changes, facial expression changes and face blur.
Keywords:
Convolutional neural network, face recognition, data augmentation
pages:
147-150
DOI:
10.35745/icice2018v2.037
Year:
2018
Published in:
2nd International Conference on Information, Communication and Engineering (ICICE 2018)
Full paper download: