Electronic Science and Technology ›› 2020, Vol. 33 ›› Issue (6): 63-68.doi: 10.16180/j.cnki.issn1007-7820.2020.06.012

Previous Articles     Next Articles

Design of Living Face Recognition System Based on Web Camera

WANG Chunjiang1,ZHANG Meng2,ZHANG Jianfei1   

  1. 1. China Air-borne Missile Academy, Luoyang 471000, China
    2. School of Artificial Antelligence, Xidian University, Xi’an 170071, China;
  • Received:2019-06-11 Online:2020-06-15 Published:2020-06-18
  • Supported by:
    National Natural Science Foundation of China(61372071)

Abstract: Aim

ing at the problems of large size, single function and high cost of the current monitoring system platform, this paper designs an online living face recognition system based on the HiSilicon 3518E platform. The system includes five parts: image pre-processing, image acquisition, face detection, face live detection, and face recognition. It also improved and optimized the deficiencies of traditional algorithms in embedded platforms. The system collected the face image through the camera and preprocessed the image to provided guarantee for subsequent image feature extraction. The extended Haar feature was used to train the classifier and the Adaboost algorithm was used to cascade face detection. The detected face used HSV and Ycbcr multi-color space the COALBP and LPQ fusion features extracted below were used to train the SVM model, perform live face detection, and finally extract LBP features from the face image to perform face recognition, and the recognition results were displayed through the WeChat applet. The experimental results showed that the feasibility of the face recognition system based on the HiSilicon web camera had certain practical value.

Key words: face recognition, live detection, Hisilicon, face detection, ARM platform, Haar, Adaboost

CLC Number: 

  • TN919.5