Using 3D Representations of the Nasal Region for Improved Landmarking and Expression Robust Recognition

Jiangning Gao, Adrian Evans

Research output: Contribution to conferencePaper

44 Downloads (Pure)

Abstract

This paper investigates the performance of different representations of 3D human nasal region for expression robust recognition. By performing evaluations on the depth and surface normal components of the facial surface, the nasal region is shown to be relatively consistent over various expressions, providing motivation for using the nasal region as a biometric. A new efficient landmarking algorithm that thresholds the local surface normal components is proposed and demonstrated to produce an improved recognition performance for nasal curves from both the depth and surface normal components. The use of the Shape Index for feature extraction is also investigated and shown to produce a good recognition performance.
Original languageEnglish
Pages4.1-4.11
Number of pages11
Publication statusPublished - 2015
Event7th UK Computer Vision Student Workshop (BMVW 2015) - , UK United Kingdom
Duration: 10 Sep 2015 → …

Workshop

Workshop7th UK Computer Vision Student Workshop (BMVW 2015)
CountryUK United Kingdom
Period10/09/15 → …

Fingerprint

Biometrics
Feature extraction

Cite this

Gao, J., & Evans, A. (2015). Using 3D Representations of the Nasal Region for Improved Landmarking and Expression Robust Recognition. 4.1-4.11. Paper presented at 7th UK Computer Vision Student Workshop (BMVW 2015), UK United Kingdom.

Using 3D Representations of the Nasal Region for Improved Landmarking and Expression Robust Recognition. / Gao, Jiangning; Evans, Adrian.

2015. 4.1-4.11 Paper presented at 7th UK Computer Vision Student Workshop (BMVW 2015), UK United Kingdom.

Research output: Contribution to conferencePaper

Gao, J & Evans, A 2015, 'Using 3D Representations of the Nasal Region for Improved Landmarking and Expression Robust Recognition' Paper presented at 7th UK Computer Vision Student Workshop (BMVW 2015), UK United Kingdom, 10/09/15, pp. 4.1-4.11.
Gao J, Evans A. Using 3D Representations of the Nasal Region for Improved Landmarking and Expression Robust Recognition. 2015. Paper presented at 7th UK Computer Vision Student Workshop (BMVW 2015), UK United Kingdom.
Gao, Jiangning ; Evans, Adrian. / Using 3D Representations of the Nasal Region for Improved Landmarking and Expression Robust Recognition. Paper presented at 7th UK Computer Vision Student Workshop (BMVW 2015), UK United Kingdom.11 p.
@conference{ebaee4f39dce4e6db38128574e618a1f,
title = "Using 3D Representations of the Nasal Region for Improved Landmarking and Expression Robust Recognition",
abstract = "This paper investigates the performance of different representations of 3D human nasal region for expression robust recognition. By performing evaluations on the depth and surface normal components of the facial surface, the nasal region is shown to be relatively consistent over various expressions, providing motivation for using the nasal region as a biometric. A new efficient landmarking algorithm that thresholds the local surface normal components is proposed and demonstrated to produce an improved recognition performance for nasal curves from both the depth and surface normal components. The use of the Shape Index for feature extraction is also investigated and shown to produce a good recognition performance.",
author = "Jiangning Gao and Adrian Evans",
year = "2015",
language = "English",
pages = "4.1--4.11",
note = "7th UK Computer Vision Student Workshop (BMVW 2015) ; Conference date: 10-09-2015",

}

TY - CONF

T1 - Using 3D Representations of the Nasal Region for Improved Landmarking and Expression Robust Recognition

AU - Gao, Jiangning

AU - Evans, Adrian

PY - 2015

Y1 - 2015

N2 - This paper investigates the performance of different representations of 3D human nasal region for expression robust recognition. By performing evaluations on the depth and surface normal components of the facial surface, the nasal region is shown to be relatively consistent over various expressions, providing motivation for using the nasal region as a biometric. A new efficient landmarking algorithm that thresholds the local surface normal components is proposed and demonstrated to produce an improved recognition performance for nasal curves from both the depth and surface normal components. The use of the Shape Index for feature extraction is also investigated and shown to produce a good recognition performance.

AB - This paper investigates the performance of different representations of 3D human nasal region for expression robust recognition. By performing evaluations on the depth and surface normal components of the facial surface, the nasal region is shown to be relatively consistent over various expressions, providing motivation for using the nasal region as a biometric. A new efficient landmarking algorithm that thresholds the local surface normal components is proposed and demonstrated to produce an improved recognition performance for nasal curves from both the depth and surface normal components. The use of the Shape Index for feature extraction is also investigated and shown to produce a good recognition performance.

UR - http://bmvc2015.swansea.ac.uk/proceedings/bmvw/papers/paper004/index.html

M3 - Paper

SP - 4.1-4.11

ER -