TIIS (한국인터넷정보학회)
Current Result Document :
| 한글제목(Korean Title) |
Periocular Recognition Using uMLBP and Attribute Features |
| 영문제목(English Title) |
Periocular Recognition Using uMLBP and Attribute Features |
| 저자(Author) |
Zahid Ali
Unsang Park
Jongho Nang
Jeong-Seon Park
Taehwa Hong
Sungjoo Park
|
| 원문수록처(Citation) |
VOL 11 NO. 12 PP. 6133 ~ 6151 (2017. 12) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
The field of periocular biometrics has gained wide attention as an alternative or supplemental means to conventional biometric traits such as the iris or the face. Periocular biometrics provide intermediate resolution between the iris and the face, which enables it to support both. We have developed a periocular recognition system by using uniform Multiscale Local Binary Pattern (uMLBP) and attribute features. The proposed system has been evaluated in terms of major factors that need to be considered on a mobile platform (e.g., distance and facial pose) to assess the feasibility of the use of periocular biometrics on mobile devices. Experimental results showed 98.7% of rank-1 identification accuracy on a subset of the Face Recognition Grand Challenge (FRGC) database, which is the best performance among similar studies.
|
| 키워드(Keyword) |
periocular biometrics
uMLBP
periocular attribute classifiers
partial least squares
FRGC
|
| 파일첨부 |
PDF 다운로드
|
