DIGITAL LIBRARY ARCHIVE
HOME > DIGITAL LIBRARY ARCHIVE
< Previous   List   Next >  
Re-classifying Method for Face Recognition
Full-text Download
Kyoung-Yul Bae (Dept. of Software, Sang-Myung University)
Vol. 10, No. 3, Page: 105 ~ 114
Keywords
Biometrics, Face Recognition, Data Classification, Face Data Re-Classification
Abstract
In the past year, the increasing concern about the biometric recognition makes the great activities on the security fields, such as the entrance control or user authentication. In particular, although the features of face recognition, such as user friendly and non-contact made it to be used widely, unhappily it has some disadvantages of low accuracy or low Re-attempts Rates. For this reason, I suggest the new approach to re-classify the classified data of recognition result data to solve the problems. For this study, I will use the typical appearance-based, PCA(Principal Component Analysis) algorithm and verify the performance improvement by adopting the re-classification approach using 200 peoples (10 pictures per one person).
Show/Hide Detailed Information in Korean
얼굴 인식 성능 향상을 위한 재분류 방법
배경률 (상명대학교 소프트웨어학부)
Keywords
생체인식, 얼굴인식, 데이터 분류 방법, 얼굴 데이터 재분류
Abstract
최근 생체인식에 대한 관심이 증가하면서 출입 통제나 사용자 인증과 같은 보안 분야에 적용이 활발히 진행되고 있다. 특히 얼굴인식은 생체인식 기술 중 사용자 편의성과 접촉 거부감이 적어 활용성이 증대되고 있으나 타 인식기술에 비해 인식 결과의 정확성과 재시도율(Re-attempt Rate)에 취약한 단점이 있다. 본 논문에서는 이러한 단점을 보완하기 위해 데이터 분류 방법(Data Classification Algorithm)으로 인식 결과를 재분류(Re-Classification)하는 접근법에 대해서 제안하고자 한다. 본 실험을 위해서 대표적인 형상 기반(Appearance-based) 알고리즘인 PCA를 사용하였고, 200명(총 얼굴 영상 200장)을 대상으로 제안한 재분류 접근법을 적용한 결과 재인식의 경우 성능이 향상되었음을 확인하였다.
Cite this article
JIIS Style
Bae, K.-Y., , "Re-classifying Method for Face Recognition", Journal of Intelligence and Information Systems, Vol. 10, No. 3 (2004), 105~114.

IEEE Style
Kyoung-Yul Bae, "Re-classifying Method for Face Recognition", Journal of Intelligence and Information Systems, vol. 10, no. 3, pp. 105~114, 2004.

ACM Style
Bae, K.-Y.,, 2004. Re-classifying Method for Face Recognition. Journal of Intelligence and Information Systems. 10, 3, 105--114.
Export Formats : BiBTeX, EndNote
Advanced Search
Date Range

to
Search
@article{Bae:JIIS:2004:211,
author = {Bae, Kyoung-Yul},
title = {Re-classifying Method for Face Recognition},
journal = {Journal of Intelligence and Information Systems},
issue_date = {December 2004},
volume = {10},
number = {3},
month = Dec,
year = {2004},
issn = {2288-4866},
pages = {105--114},
url = {},
doi = {},
publisher = {Korea Intelligent Information System Society},
address = {Seoul, Republic of Korea},
keywords = { Biometrics, Face Recognition, Data Classification and Face Data Re-Classification },
}
%0 Journal Article
%1 211
%A Kyoung-Yul Bae
%T Re-classifying Method for Face Recognition
%J Journal of Intelligence and Information Systems
%@ 2288-4866
%V 10
%N 3
%P 105-114
%D 2004
%R
%I Korea Intelligent Information System Society