Nasal patches and curves for expression-robust 3D face recognition

Mehryar Emambakhsh, Adrian Evans

Research output: Contribution to journalArticle

21 Citations (Scopus)
62 Downloads (Pure)

Abstract

The potential of the nasal region for expression robust 3D face recognition is thoroughly investigated by a novel five-step algorithm. First, the nose tip location is coarsely detected and the face is segmented, aligned and the nasal region cropped. Then, a very accurate and consistent nasal landmarking algorithm detects seven keypoints on the nasal region. In the third step, a feature extraction algorithm based on the surface normals of Gabor-wavelet filtered depth maps is utilised and, then, a set of spherical patches and curves are localised over the nasal region to provide the feature descriptors. The last step applies a genetic algorithm-based feature selector to detect the most stable patches and curves over different facial expressions. The algorithm provides the highest reported nasal region-based recognition ranks on the FRGC, Bosphorus and BU-3DFE datasets. The results are comparable with, and in many cases better than, many state-of-the-art 3D face recognition algorithms, which use the whole facial domain. The proposed method does not rely on sophisticated alignment or denoising steps, is very robust when only one sample per subject is used in the gallery, and does not require a training step for the landmarking algorithm.
Original languageEnglish
Pages (from-to)995-1007
Number of pages13
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume39
Issue number5
Early online date10 May 2016
DOIs
Publication statusPublished - 1 May 2017

Keywords

  • Face recognition, Facial landmarking, Nose region, Feature selection, Gabor wavelets, Surface normals

Cite this

Nasal patches and curves for expression-robust 3D face recognition. / Emambakhsh, Mehryar; Evans, Adrian.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 5, 01.05.2017, p. 995-1007.

Research output: Contribution to journalArticle

@article{495e8b9b46eb43d09eefd3a07c1434e2,
title = "Nasal patches and curves for expression-robust 3D face recognition",
abstract = "The potential of the nasal region for expression robust 3D face recognition is thoroughly investigated by a novel five-step algorithm. First, the nose tip location is coarsely detected and the face is segmented, aligned and the nasal region cropped. Then, a very accurate and consistent nasal landmarking algorithm detects seven keypoints on the nasal region. In the third step, a feature extraction algorithm based on the surface normals of Gabor-wavelet filtered depth maps is utilised and, then, a set of spherical patches and curves are localised over the nasal region to provide the feature descriptors. The last step applies a genetic algorithm-based feature selector to detect the most stable patches and curves over different facial expressions. The algorithm provides the highest reported nasal region-based recognition ranks on the FRGC, Bosphorus and BU-3DFE datasets. The results are comparable with, and in many cases better than, many state-of-the-art 3D face recognition algorithms, which use the whole facial domain. The proposed method does not rely on sophisticated alignment or denoising steps, is very robust when only one sample per subject is used in the gallery, and does not require a training step for the landmarking algorithm.",
keywords = "Face recognition, Facial landmarking, Nose region, Feature selection, Gabor wavelets, Surface normals",
author = "Mehryar Emambakhsh and Adrian Evans",
year = "2017",
month = "5",
day = "1",
doi = "10.1109/TPAMI.2016.2565473",
language = "English",
volume = "39",
pages = "995--1007",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE",
number = "5",

}

TY - JOUR

T1 - Nasal patches and curves for expression-robust 3D face recognition

AU - Emambakhsh, Mehryar

AU - Evans, Adrian

PY - 2017/5/1

Y1 - 2017/5/1

N2 - The potential of the nasal region for expression robust 3D face recognition is thoroughly investigated by a novel five-step algorithm. First, the nose tip location is coarsely detected and the face is segmented, aligned and the nasal region cropped. Then, a very accurate and consistent nasal landmarking algorithm detects seven keypoints on the nasal region. In the third step, a feature extraction algorithm based on the surface normals of Gabor-wavelet filtered depth maps is utilised and, then, a set of spherical patches and curves are localised over the nasal region to provide the feature descriptors. The last step applies a genetic algorithm-based feature selector to detect the most stable patches and curves over different facial expressions. The algorithm provides the highest reported nasal region-based recognition ranks on the FRGC, Bosphorus and BU-3DFE datasets. The results are comparable with, and in many cases better than, many state-of-the-art 3D face recognition algorithms, which use the whole facial domain. The proposed method does not rely on sophisticated alignment or denoising steps, is very robust when only one sample per subject is used in the gallery, and does not require a training step for the landmarking algorithm.

AB - The potential of the nasal region for expression robust 3D face recognition is thoroughly investigated by a novel five-step algorithm. First, the nose tip location is coarsely detected and the face is segmented, aligned and the nasal region cropped. Then, a very accurate and consistent nasal landmarking algorithm detects seven keypoints on the nasal region. In the third step, a feature extraction algorithm based on the surface normals of Gabor-wavelet filtered depth maps is utilised and, then, a set of spherical patches and curves are localised over the nasal region to provide the feature descriptors. The last step applies a genetic algorithm-based feature selector to detect the most stable patches and curves over different facial expressions. The algorithm provides the highest reported nasal region-based recognition ranks on the FRGC, Bosphorus and BU-3DFE datasets. The results are comparable with, and in many cases better than, many state-of-the-art 3D face recognition algorithms, which use the whole facial domain. The proposed method does not rely on sophisticated alignment or denoising steps, is very robust when only one sample per subject is used in the gallery, and does not require a training step for the landmarking algorithm.

KW - Face recognition, Facial landmarking, Nose region, Feature selection, Gabor wavelets, Surface normals

UR - http://dx.doi.org/10.1109/TPAMI.2016.2565473

U2 - 10.1109/TPAMI.2016.2565473

DO - 10.1109/TPAMI.2016.2565473

M3 - Article

VL - 39

SP - 995

EP - 1007

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 5

ER -