Local feature based 3D face recognition

Yonguk Lee, Hwanjong Song, Ukil Yang, Hyungchul Shin, Kwanghoon Sohn

Research output: Contribution to journalConference article

33 Citations (Scopus)

Abstract

This paper presents a 3D face recognition system based on geometrically localized facial features. We propose the feature extraction procedure using the geometrical characteristics of a face. We extract three curvatures, eight invariant facial feature points and their relative features. These features are directly applied to face recognition algorithms which are a depth-based DP (Dynamic Programming) and a feature-based SVM (Support Vector Machine). Experimental results show that face recognition rates based on the depth-based DP and the feature-based SVM are 95% for 20 people and 96% for 100 people, respectively.

Original languageEnglish
Pages (from-to)909-918
Number of pages10
JournalLecture Notes in Computer Science
Volume3546
Publication statusPublished - 2005 Oct 17

Fingerprint

Local Features
Face recognition
Face Recognition
Dynamic programming
Dynamic Programming
Support vector machines
Support Vector Machine
Feature Point
Recognition Algorithm
Feature Extraction
Feature extraction
Curvature
Face
Invariant
Experimental Results

All Science Journal Classification (ASJC) codes

  • Computer Science (miscellaneous)

Cite this

Lee, Y., Song, H., Yang, U., Shin, H., & Sohn, K. (2005). Local feature based 3D face recognition. Lecture Notes in Computer Science, 3546, 909-918.
Lee, Yonguk ; Song, Hwanjong ; Yang, Ukil ; Shin, Hyungchul ; Sohn, Kwanghoon. / Local feature based 3D face recognition. In: Lecture Notes in Computer Science. 2005 ; Vol. 3546. pp. 909-918.
@article{1f1c2e44292b41ecb33ebce502e1f5ce,
title = "Local feature based 3D face recognition",
abstract = "This paper presents a 3D face recognition system based on geometrically localized facial features. We propose the feature extraction procedure using the geometrical characteristics of a face. We extract three curvatures, eight invariant facial feature points and their relative features. These features are directly applied to face recognition algorithms which are a depth-based DP (Dynamic Programming) and a feature-based SVM (Support Vector Machine). Experimental results show that face recognition rates based on the depth-based DP and the feature-based SVM are 95{\%} for 20 people and 96{\%} for 100 people, respectively.",
author = "Yonguk Lee and Hwanjong Song and Ukil Yang and Hyungchul Shin and Kwanghoon Sohn",
year = "2005",
month = "10",
day = "17",
language = "English",
volume = "3546",
pages = "909--918",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",

}

Lee, Y, Song, H, Yang, U, Shin, H & Sohn, K 2005, 'Local feature based 3D face recognition', Lecture Notes in Computer Science, vol. 3546, pp. 909-918.

Local feature based 3D face recognition. / Lee, Yonguk; Song, Hwanjong; Yang, Ukil; Shin, Hyungchul; Sohn, Kwanghoon.

In: Lecture Notes in Computer Science, Vol. 3546, 17.10.2005, p. 909-918.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Local feature based 3D face recognition

AU - Lee, Yonguk

AU - Song, Hwanjong

AU - Yang, Ukil

AU - Shin, Hyungchul

AU - Sohn, Kwanghoon

PY - 2005/10/17

Y1 - 2005/10/17

N2 - This paper presents a 3D face recognition system based on geometrically localized facial features. We propose the feature extraction procedure using the geometrical characteristics of a face. We extract three curvatures, eight invariant facial feature points and their relative features. These features are directly applied to face recognition algorithms which are a depth-based DP (Dynamic Programming) and a feature-based SVM (Support Vector Machine). Experimental results show that face recognition rates based on the depth-based DP and the feature-based SVM are 95% for 20 people and 96% for 100 people, respectively.

AB - This paper presents a 3D face recognition system based on geometrically localized facial features. We propose the feature extraction procedure using the geometrical characteristics of a face. We extract three curvatures, eight invariant facial feature points and their relative features. These features are directly applied to face recognition algorithms which are a depth-based DP (Dynamic Programming) and a feature-based SVM (Support Vector Machine). Experimental results show that face recognition rates based on the depth-based DP and the feature-based SVM are 95% for 20 people and 96% for 100 people, respectively.

UR - http://www.scopus.com/inward/record.url?scp=26444603416&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26444603416&partnerID=8YFLogxK

M3 - Conference article

VL - 3546

SP - 909

EP - 918

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

ER -

Lee Y, Song H, Yang U, Shin H, Sohn K. Local feature based 3D face recognition. Lecture Notes in Computer Science. 2005 Oct 17;3546:909-918.