Open AccessFace Recognition Based on Deep Learning of Small Data Set
Author(s) -
Lichun Yu,
Jinqing Liu
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1624/5/052004
Subject(s) - facial recognition system , computer science , artificial intelligence , face (sociological concept) , training set , three dimensional face recognition , deep learning , data set , pattern recognition (psychology) , machine learning , scale (ratio) , set (abstract data type) , face detection , social science , physics , quantum mechanics , sociology , programming language
Face recognition based on deep learning relies on large-scale label data, which limits the application of face recognition technology. To solve this problem, this paper proposes an improved VGGNet algorithm for face recognition. The improved algorithm requires less training data size, faster training speed, and the face recognition rate reaches more than 95%, which can meet the practical application requirements of most scenes.