人脸识别考勤系统中有效人脸特征提取

上海大学学报(自然科学版)

人脸识别考勤系统中有效人脸特征提取

张婷，朱秋煜，朱军林

上海大学通信与信息工程学院，上海 200072

收稿日期:2005-08-05 修回日期:1900-01-01 出版日期:2006-06-30 发布日期:2006-06-30
通讯作者: 朱秋煜

Efficient Feature Extraction in an Attendance System -Based on Face Recognition

ZHANG Ting,ZHU Qiu-yu,ZHU Jun-lin

School of Communication and Information Engineering, Shanghai University, Shanghai 200072, China

Received:2005-08-05 Revised:1900-01-01 Online:2006-06-30 Published:2006-06-30
Contact: ZHU Qiu-yu

摘要/Abstract

摘要：

提出了一种适用于考勤系统的人脸识别算法.该算法首先从2台摄像机实时采集的正、侧面图像中分割出人脸区域，然后对图像中的人脸进行有效几何特征的提取，并构造出特征矢量与持卡者所持有的卡片中信息进行比对.经实验验证本系统算法简单、定位准确、识别率较高.

关键词: 考勤系统, 人脸识别, 特征矢量, 正、侧面图像

Abstract:

A face recognition method applicable to attendance systems is proposed. Areas of a face image are first segmented from facial frontal and facial profile images that are dynamically captured with a camera. Effective geometric feature points extracted from the face regions are then used to construct feature vectors. These feature vectors are compared with the vector information in the card held by the subject. The algorithm is simple, and a high recognition rate has been achieved in the experiments.

Key words: face recognition, facial frontal and profile image, feature vector

attendance system

张婷;朱秋煜;朱军林. 人脸识别考勤系统中有效人脸特征提取[J]. 上海大学学报(自然科学版).

ZHANG Ting;ZHU Qiu-yu;ZHU Jun-lin. Efficient Feature Extraction in an Attendance System -Based on Face Recognition[J]. Journal of Shanghai University（Natural Science Edition）.

[1]	冉鹏, 王灵, 李昕, 刘鹏伟. 改进Softmax分类器的深度卷积神经网络及其在人脸识别中的应用[J]. 上海大学学报(自然科学版), 2018, 24(3): 352-366.
[2]	郎玥1, 周霁婷1, 梁小龙2, 张文俊1. 基于人脸识别的影视剧镜头自动标注及重剪系统[J]. 上海大学学报(自然科学版), 2017, 23(3): 353-363.
[3]	黄翠荣;严佩敏;时鹿鸣. 基于方差相似度计算的人脸识别技术[J]. 上海大学学报(自然科学版), 2006, 12(4): 347-350 .