On the false rejection ratio of face recognition based on automatic detected feature points

Kazuo Ohzeki; Masahiro Takatsuka; Masaaki Kajihara; Yutaka Hirakawa; Kiyotsugu Sato

doi:10.1134/S1054661816020073

On the false rejection ratio of face recognition based on automatic detected feature points

Kazuo Ohzeki, Masahiro Takatsuka, Masaaki Kajihara, Yutaka Hirakawa, Kiyotsugu Sato

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

The authors propose a new face recognition system with an evaluation function using feature points. The feature points are detected automatically by Milborrow’s Stasm software. Before recognition, rotation compensation and size normalization are applied to the feature points. The main method is to calculate the squared error between the registered face and the input face as to length of a characteristic pair of feature points on face. The False Rejection Rate (FRR) for the registered and input face of the same person, and the False Acceptance Rate (FAR) for the registered face and a different person’s input face are evaluated. The input is a video sequence. Stable recognition is obtained with small FRR and FAR for the video of a period of 0.5 s.

Original language	English
Pages (from-to)	379-384
Number of pages	6
Journal	Pattern Recognition and Image Analysis
Volume	26
Issue number	2
DOIs	https://doi.org/10.1134/S1054661816020073
Publication status	Published - 2016 Apr 1

Keywords

face recognition
feature points
individual characteristics
normalization
rotation compensation

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Computer Graphics and Computer-Aided Design

Access to Document

10.1134/S1054661816020073

Cite this

@article{ec3d162eb9f344d6bc9ba19002080738,

title = "On the false rejection ratio of face recognition based on automatic detected feature points",

abstract = "The authors propose a new face recognition system with an evaluation function using feature points. The feature points are detected automatically by Milborrow{\textquoteright}s Stasm software. Before recognition, rotation compensation and size normalization are applied to the feature points. The main method is to calculate the squared error between the registered face and the input face as to length of a characteristic pair of feature points on face. The False Rejection Rate (FRR) for the registered and input face of the same person, and the False Acceptance Rate (FAR) for the registered face and a different person{\textquoteright}s input face are evaluated. The input is a video sequence. Stable recognition is obtained with small FRR and FAR for the video of a period of 0.5 s.",

keywords = "face recognition, feature points, individual characteristics, normalization, rotation compensation",

author = "Kazuo Ohzeki and Masahiro Takatsuka and Masaaki Kajihara and Yutaka Hirakawa and Kiyotsugu Sato",

year = "2016",

month = apr,

day = "1",

doi = "10.1134/S1054661816020073",

language = "English",

volume = "26",

pages = "379--384",

journal = "Pattern Recognition and Image Analysis",

issn = "1054-6618",

publisher = "Maik Nauka-Interperiodica Publishing",

number = "2",

}

TY - JOUR

T1 - On the false rejection ratio of face recognition based on automatic detected feature points

AU - Ohzeki, Kazuo

AU - Takatsuka, Masahiro

AU - Kajihara, Masaaki

AU - Hirakawa, Yutaka

AU - Sato, Kiyotsugu

PY - 2016/4/1

Y1 - 2016/4/1

N2 - The authors propose a new face recognition system with an evaluation function using feature points. The feature points are detected automatically by Milborrow’s Stasm software. Before recognition, rotation compensation and size normalization are applied to the feature points. The main method is to calculate the squared error between the registered face and the input face as to length of a characteristic pair of feature points on face. The False Rejection Rate (FRR) for the registered and input face of the same person, and the False Acceptance Rate (FAR) for the registered face and a different person’s input face are evaluated. The input is a video sequence. Stable recognition is obtained with small FRR and FAR for the video of a period of 0.5 s.

AB - The authors propose a new face recognition system with an evaluation function using feature points. The feature points are detected automatically by Milborrow’s Stasm software. Before recognition, rotation compensation and size normalization are applied to the feature points. The main method is to calculate the squared error between the registered face and the input face as to length of a characteristic pair of feature points on face. The False Rejection Rate (FRR) for the registered and input face of the same person, and the False Acceptance Rate (FAR) for the registered face and a different person’s input face are evaluated. The input is a video sequence. Stable recognition is obtained with small FRR and FAR for the video of a period of 0.5 s.

KW - face recognition

KW - feature points

KW - individual characteristics

KW - normalization

KW - rotation compensation

UR - http://www.scopus.com/inward/record.url?scp=84975841262&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975841262&partnerID=8YFLogxK

U2 - 10.1134/S1054661816020073

DO - 10.1134/S1054661816020073

M3 - Article

AN - SCOPUS:84975841262

SN - 1054-6618

VL - 26

SP - 379

EP - 384

JO - Pattern Recognition and Image Analysis

JF - Pattern Recognition and Image Analysis

IS - 2

ER -

On the false rejection ratio of face recognition based on automatic detected feature points

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this