Fumiya SAITO’s research while affiliated with Nagoya University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (5)


Personal Authentication Using a Kinect Sensor
  • Article

November 2017

·

54 Reads

·

2 Citations

The Review of Socionetwork Strategies

Xuanang Feng

·

·

Eisuke Kita

·

Fumiya Saito

This article proposes a new approach to personal authentication by exploring the features of a person’s face and voice. Microsoft’s Kinect sensor is used for facial and voice recognition. Parts of the face including the eyes, nose, and mouth, etc., are analyzed as position vectors. For voice recognition, a Kinect microphone array is adopted to record personal voices. Mel-frequency cepstrum coefficients, logarithmic power, and related values involved in the analysis of personal voice are also estimated from the voices. Neural networks,support vector machines and principal components analysis are employed and compared for personal authentication. To achieve accurate results, 20 examinees were selected for face and voice data used for training the authentication models. The experimental results show that the best accuracy is achieved when the model is trained by a support vector machine using both facial and voice features.



1406 Study on Personal Authentication by Kinect Sensor

September 2014

·

24 Reads

·

1 Citation

The Proceedings of Design & Systems Conference

Importance of personal authentication increases according to the progress of advanced information society and web service. This paper describes the personal authentication by using Kinect sensor. Feature quantities of the human face and the human voice are obtained through the Kinect sensor. Personal authentication is performed with the machine learning algorithms with the feature quantities. The neural network, support vector machine and Bayesian network are compared in the experimental results. The results show that the neural network is the most promising.


3108 Facial Recognition System by Using Kinect

October 2013

·

8 Reads

The Proceedings of Design & Systems Conference

Fumiya SAITO

·

Xuanang FENG

·

Azusa HARA

·

[...]

·

Eisuke KITA

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.


2506 Smart control of automatic door through NUI

October 2013

·

15 Reads

The Proceedings of Design & Systems Conference

The purpose of this research is to develop an automatic door system, which can provide intelligent opening and closing operations. The automatic door is not opened when a pedestrian just passes by the door. In order to judge the intention of the pedestrian whether he wants to pass through the door, we detect the pedestrian's skeleton data, joint orientation, and 3D coordinates by using Kinect sensor. In this paper, we analyze the behavior of pedestrians from the extracted features, and propose a method what can calculate width of pedestrian and the appropriate timing of opening operation for only whom determining to pass through the door.

Citations (1)


... In previous study, the Mel-frequency cepstrum coefficients, the logarithmic power and their related values are calculated from the personal voice [8]. Another study in [9] was on facial depth data of a speaking subject, captured by the Kinect device, as an additional speech informative modality to incorporate to a traditional audiovisual automatic speech recognizer. ...

Reference:

Human Identification through Kinect’s Depth, RGB, and Sound Sensor
Personal Identification with Face and Voice Features Extracted through Kinect Sensor
  • Citing Conference Paper
  • December 2016