The Proceedings of Design & Systems Conference
Online ISSN : 2424-3078
2013.23
Session ID : 3108
Conference information
3108 Facial Recognition System by Using Kinect
Fumiya SAITOXuanang FENGAzusa HARAMiki MIYACHIEisuke KITA
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract
According to progress of information society, the importance of personal authentication is growing by leaps and bounds. Because it dose not require a specific act or behavior, facial recognition is the focus of attention than other biometric identifications. The purpose of this reserch is method of extracting feature values of a human face by using Kinect sensor that is relatively inexpensive compared to the other depth cameras. And examine Kinect sensor whether the effective device for facial recognition system. In this paper,compared Neural Network, Support Vector Machine, Bayesian Network as a decision algorithm of the individual. From experimental results using still images of 10 subjects, relevance ratio of Neural Network showed the highest rate 95.6%,and considered the this method and the results.
Content from these authors
© 2013 The Japan Society of Mechanical Engineers
Previous article Next article
feedback
Top