The review and results of different methods for facial recognition

2017 2nd International Seminar on Advances in Materials Science and Engineering

Le, Yifan^1

School of Physics and Electronics, Central South University, Hunan

410083, China^1

关键词: Biometric identifications;    Facial landmark detection;    Facial recognition;    Human behavior understanding;    Improvement measure;    Learning-based methods;    Localization effect;    State-of-the-art methods;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/231/1/012021/pdf
DOI  :  10.1088/1757-899X/231/1/012021

来源: IOP

【 摘 要 】

In recent years, facial recognition draws much attention due to its wide potential applications. As a unique technology in Biometric Identification, facial recognition represents a significant improvement since it could be operated without cooperation of people under detection. Hence, facial recognition will be taken into defense system, medical detection, human behavior understanding, etc. Several theories and methods have been established to make progress in facial recognition: (1) A novel two-stage facial landmark localization method is proposed which has more accurate facial localization effect under specific database; (2) A statistical face frontalization method is proposed which outperforms state-of-the-art methods for face landmark localization; (3) It proposes a general facial landmark detection algorithm to handle images with severe occlusion and images with large head poses; (4) There are three methods proposed on Face Alignment including shape augmented regression method, pose-indexed based multi-view method and a learning based method via regressing local binary features. The aim of this paper is to analyze previous work of different aspects in facial recognition, focusing on concrete method and performance under various databases. In addition, some improvement measures and suggestions in potential applications will be put forward.