摘要
针对复杂应用场景下人脸识别系统效率低、实时性差和证件信息运用不充分等问题,设计了基于人脸识别技术的人证比对系统.将该系统应用于多人脸视频场景中,可缩小人脸检测识别范围,提高识别速度和识别率,解决了复杂场景下人脸比对效率低的问题;采用补偿光的办法,解决了强背光对人脸图像检测及特征提取产生的影响.
In order to solve the problem of low efficiency,poor real-time and insufficient use of identity information in face recognition system in complex scenes,this paper presents a face verification system based on face recognition technology.This system defines the region of interest for multi-face videos.It can narrow the range of face detection and recognition,improve recognition speed and accuracy in complex scenes.To reduce the impact of strong backlight on face detection and feature extraction,light compensation method is applied.
作者
王祺
田青
赵歌
曲洪权
WANG Qi;TIAN Qing;ZHAO Ge;QU Hongquan(College of Electronic Information Engineering,North China University of Technology,Beijing100144,China)
出处
《吉首大学学报(自然科学版)》
CAS
2018年第4期15-19,共5页
Journal of Jishou University(Natural Sciences Edition)
基金
国家重点研发计划项目(2017YFC0806005)
北京市科技计划项目(Z161100001016003)
关键词
人脸识别
人证比对
人脸图像
数据库
face recognition
comparison of human evidence
face image
data base