Using bidimensional regression to assess face similarity

Sarvani Kare, Ashok K Samal, David Marx

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Face recognition is the identification of humans by the unique characteristics of their faces and forms the basis for many biometric systems. In this research the problem of feature-based face recognition is considered. Bidimensional regression (BDR) is an extension of standard regression to2D variables. Bidimensional regression can be used to determine the degree of resemblance between two planar configurations of points and for assessing the nature of their geometry. A primary advantage of this approach is that no training is needed. The goal of this research is to explore the suitability of BDR for 2D matching. Specifically, we explore if bidimensional regression can be used as a basis for a similarity measure to compare faces. The approach is tested using standard datasets. The results show that BDR can be effective in recognizing faces and hence can be used as an effective 2D matching technique.

Original languageEnglish (US)
Pages (from-to)261-274
Number of pages14
JournalMachine Vision and Applications
Volume21
Issue number3
DOIs
StatePublished - Apr 1 2010

Fingerprint

Face recognition
Biometrics
Geometry

Keywords

  • Bidimensional regression
  • Face recognition
  • Landmarks

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Using bidimensional regression to assess face similarity. / Kare, Sarvani; Samal, Ashok K; Marx, David.

In: Machine Vision and Applications, Vol. 21, No. 3, 01.04.2010, p. 261-274.

Research output: Contribution to journalArticle

Kare, Sarvani ; Samal, Ashok K ; Marx, David. / Using bidimensional regression to assess face similarity. In: Machine Vision and Applications. 2010 ; Vol. 21, No. 3. pp. 261-274.
@article{9a90a22cbcde4f1bb09f7bef20756f0f,
title = "Using bidimensional regression to assess face similarity",
abstract = "Face recognition is the identification of humans by the unique characteristics of their faces and forms the basis for many biometric systems. In this research the problem of feature-based face recognition is considered. Bidimensional regression (BDR) is an extension of standard regression to2D variables. Bidimensional regression can be used to determine the degree of resemblance between two planar configurations of points and for assessing the nature of their geometry. A primary advantage of this approach is that no training is needed. The goal of this research is to explore the suitability of BDR for 2D matching. Specifically, we explore if bidimensional regression can be used as a basis for a similarity measure to compare faces. The approach is tested using standard datasets. The results show that BDR can be effective in recognizing faces and hence can be used as an effective 2D matching technique.",
keywords = "Bidimensional regression, Face recognition, Landmarks",
author = "Sarvani Kare and Samal, {Ashok K} and David Marx",
year = "2010",
month = "4",
day = "1",
doi = "10.1007/s00138-008-0158-7",
language = "English (US)",
volume = "21",
pages = "261--274",
journal = "Machine Vision and Applications",
issn = "0932-8092",
publisher = "Springer Verlag",
number = "3",

}

TY - JOUR

T1 - Using bidimensional regression to assess face similarity

AU - Kare, Sarvani

AU - Samal, Ashok K

AU - Marx, David

PY - 2010/4/1

Y1 - 2010/4/1

N2 - Face recognition is the identification of humans by the unique characteristics of their faces and forms the basis for many biometric systems. In this research the problem of feature-based face recognition is considered. Bidimensional regression (BDR) is an extension of standard regression to2D variables. Bidimensional regression can be used to determine the degree of resemblance between two planar configurations of points and for assessing the nature of their geometry. A primary advantage of this approach is that no training is needed. The goal of this research is to explore the suitability of BDR for 2D matching. Specifically, we explore if bidimensional regression can be used as a basis for a similarity measure to compare faces. The approach is tested using standard datasets. The results show that BDR can be effective in recognizing faces and hence can be used as an effective 2D matching technique.

AB - Face recognition is the identification of humans by the unique characteristics of their faces and forms the basis for many biometric systems. In this research the problem of feature-based face recognition is considered. Bidimensional regression (BDR) is an extension of standard regression to2D variables. Bidimensional regression can be used to determine the degree of resemblance between two planar configurations of points and for assessing the nature of their geometry. A primary advantage of this approach is that no training is needed. The goal of this research is to explore the suitability of BDR for 2D matching. Specifically, we explore if bidimensional regression can be used as a basis for a similarity measure to compare faces. The approach is tested using standard datasets. The results show that BDR can be effective in recognizing faces and hence can be used as an effective 2D matching technique.

KW - Bidimensional regression

KW - Face recognition

KW - Landmarks

UR - http://www.scopus.com/inward/record.url?scp=77953359146&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953359146&partnerID=8YFLogxK

U2 - 10.1007/s00138-008-0158-7

DO - 10.1007/s00138-008-0158-7

M3 - Article

VL - 21

SP - 261

EP - 274

JO - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 3

ER -