Student authentication by updated facial information with weighting coefficient in e-Learning

E-Learning is effective for reducing time and space limitations for learners. However, one drawback is that user authentication generally employs only login credentials, making cheating easy. We examine variations in facial images in e-Learning with the aim of detecting spoofing. We propose an authe...

Full description

Saved in:
Bibliographic Details
Main Authors: Kawamata, Taisuke, Ishii, Takatoshi, Fujimori, Susumu, Akakura, Takako
Format: Conference Proceeding
Language:English
Subjects:
Authentication
Electronic learning
Face
Face detection
Proposals
Timing
Webcams
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:E-Learning is effective for reducing time and space limitations for learners. However, one drawback is that user authentication generally employs only login credentials, making cheating easy. We examine variations in facial images in e-Learning with the aim of detecting spoofing. We propose an authentication method that updates registered image using sequential facial images taken by a webcam during e-Learning sessions. This paper examines update timing and procedures, and finds that the updating based on weighted summation of facial feature vectors at students' operation timing maximizes authentication accuracy.
ISSN:2159-3450
DOI:10.1109/TENCON.2016.7848061