Open AccessIdentity Recognition Based on Face Image
Author(s) -
Qin Chen,
Xiaobo Lu,
Pengguo Zhang,
Huibin Xie,
Wenbin Zeng
Publication year - 2019
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 - 10.1088/1742-6596/1302/3/032049
Subject(s) - artificial intelligence , computer science , face (sociological concept) , computer vision , three dimensional face recognition , face detection , object class detection , feature extraction , facial recognition system , identity (music) , pattern recognition (psychology) , feature (linguistics) , process (computing) , variation (astronomy) , image (mathematics) , set (abstract data type) , image processing , linguistics , philosophy , social science , physics , sociology , acoustics , astrophysics , programming language , operating system
This article is aimed at designing a human identity recognition algorithm based on face image, which will be used in indoor environment. As the working environment is set as indoor environment, the camera will not be affected much by illumination variation. The key is how to detect human face and handle the variation of facial pose. This article divides the whole recognition process into 4 parts: image pre-processing, face detection, face alignment, feature extraction and comparison. Face detection and feature extraction are the core functions and both realized by deep learning. The process of the whole algorithm can be described as following: images after pre-processing are fed to face detection network to get the locations of face and face landmarks. Then face alignment will be conducted. Finally, deep features of face will be extracted and compared. The unique features of this algorithm are its good performance of handling the variation of facial pose and its clear framework which allows the whole method can be easily adjusted and upgraded.