|
Title:
|
USER IDENTIFICATION IN LEARNING MANAGEMENT SYSTEMS BASED ON FACE RECOGNITION FROM VIDEO |
|
Author(s):
|
Guilherme José da Costa Kami, Aparecido Nilceu Marana, Bruno Elias Penteado |
|
ISBN:
|
978-989-8533-06-7 |
|
Editors:
|
Hans Weghorn, Leonardo Azevedo and Pedro Isaías |
|
Year:
|
2011 |
|
Edition:
|
Single |
|
Keywords:
|
LMS, Biometrics, Face Recognition, Video, Pattern Classifiers |
|
Type:
|
Full Paper |
|
First Page:
|
347 |
|
Last Page:
|
354 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
During the last decades it has been observed a proliferation of web-based courses, managed by Learning Management Systems (LMS). In general, LMS adopt passwords for user identification. However, the use of this simple type of identification increases vulnerability to fraud. In the last years, biometric devices are becoming cheaper and are being embedded into most computers and mobile devices. Therefore, nowadays biometrics is considered a promising alternative to passwords for user identification in LMS. In this work, we have improved the video-based face recognition module of an experimental system proposed for user identification in LMS. This improvement consists in replacing the use of dissimilarity measures by pattern classifiers for the face recognition. Experimental results on Honda/UCSD and Recogna Video Databases showed that the use of OPF and SVM classifiers significantly improved the face recognition accuracy rates in the experimental system. To the best of our knowledge, this is the first time that OPF has been used for face recognition from video. |
|
|
|
|
|
|
