A two-phase weighted collaborative representation for 3D partial face recognition with single sample

Yinjie Lei, Yulan Guo, Munawar Hayat, Mohammed Bennamoun, Xinzhi Zhou

Research output: Contribution to journalArticle

40 Citations (Scopus)
1 Downloads (Pure)

Abstract

3D face recognition with the availability of only partial data (missing parts, occlusions and data corruptions) and single training sample is a highly challenging task. This paper presents an efficient 3D face recognition approach to address this challenge. We represent a facial scan with a set of local Keypoint-based Multiple Triangle Statistics (KMTS), which is robust to partial facial data, large facial expressions and pose variations. To address the single sample problem, we then propose a Two-Phase Weighted Collaborative Representation Classification (TPWCRC) framework. A class-based probability estimation is first calculated based on the extracted local descriptors as a prior knowledge. The resulting class-based probability estimation is then incorporated into the proposed classification framework as a locality constraint to further enhance its discriminating power. Experimental results on six challenging 3D facial datasets show that the proposed KMTS–TPWCRC framework achieves promising results for human face recognition with missing parts, occlusions, data corruptions, expressions and pose variations
Original languageEnglish
Pages (from-to)218-237
Number of pages20
JournalPattern Recognition
Volume52
Issue number1
DOIs
Publication statusPublished - 2016
Externally publishedYes

Fingerprint

Face recognition
Statistics
Availability

Cite this

Lei, Yinjie ; Guo, Yulan ; Hayat, Munawar ; Bennamoun, Mohammed ; Zhou, Xinzhi. / A two-phase weighted collaborative representation for 3D partial face recognition with single sample. In: Pattern Recognition. 2016 ; Vol. 52, No. 1. pp. 218-237.
@article{9d1e9c21e7b14eeab917b2a6e7384cc6,
title = "A two-phase weighted collaborative representation for 3D partial face recognition with single sample",
abstract = "3D face recognition with the availability of only partial data (missing parts, occlusions and data corruptions) and single training sample is a highly challenging task. This paper presents an efficient 3D face recognition approach to address this challenge. We represent a facial scan with a set of local Keypoint-based Multiple Triangle Statistics (KMTS), which is robust to partial facial data, large facial expressions and pose variations. To address the single sample problem, we then propose a Two-Phase Weighted Collaborative Representation Classification (TPWCRC) framework. A class-based probability estimation is first calculated based on the extracted local descriptors as a prior knowledge. The resulting class-based probability estimation is then incorporated into the proposed classification framework as a locality constraint to further enhance its discriminating power. Experimental results on six challenging 3D facial datasets show that the proposed KMTS–TPWCRC framework achieves promising results for human face recognition with missing parts, occlusions, data corruptions, expressions and pose variations",
keywords = "face-recognition, computer-vision, image-processing",
author = "Yinjie Lei and Yulan Guo and Munawar Hayat and Mohammed Bennamoun and Xinzhi Zhou",
year = "2016",
doi = "10.1016/j.patcog.2015.09.035",
language = "English",
volume = "52",
pages = "218--237",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "1",

}

A two-phase weighted collaborative representation for 3D partial face recognition with single sample. / Lei, Yinjie; Guo, Yulan; Hayat, Munawar; Bennamoun, Mohammed; Zhou, Xinzhi.

In: Pattern Recognition, Vol. 52, No. 1, 2016, p. 218-237.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A two-phase weighted collaborative representation for 3D partial face recognition with single sample

AU - Lei, Yinjie

AU - Guo, Yulan

AU - Hayat, Munawar

AU - Bennamoun, Mohammed

AU - Zhou, Xinzhi

PY - 2016

Y1 - 2016

N2 - 3D face recognition with the availability of only partial data (missing parts, occlusions and data corruptions) and single training sample is a highly challenging task. This paper presents an efficient 3D face recognition approach to address this challenge. We represent a facial scan with a set of local Keypoint-based Multiple Triangle Statistics (KMTS), which is robust to partial facial data, large facial expressions and pose variations. To address the single sample problem, we then propose a Two-Phase Weighted Collaborative Representation Classification (TPWCRC) framework. A class-based probability estimation is first calculated based on the extracted local descriptors as a prior knowledge. The resulting class-based probability estimation is then incorporated into the proposed classification framework as a locality constraint to further enhance its discriminating power. Experimental results on six challenging 3D facial datasets show that the proposed KMTS–TPWCRC framework achieves promising results for human face recognition with missing parts, occlusions, data corruptions, expressions and pose variations

AB - 3D face recognition with the availability of only partial data (missing parts, occlusions and data corruptions) and single training sample is a highly challenging task. This paper presents an efficient 3D face recognition approach to address this challenge. We represent a facial scan with a set of local Keypoint-based Multiple Triangle Statistics (KMTS), which is robust to partial facial data, large facial expressions and pose variations. To address the single sample problem, we then propose a Two-Phase Weighted Collaborative Representation Classification (TPWCRC) framework. A class-based probability estimation is first calculated based on the extracted local descriptors as a prior knowledge. The resulting class-based probability estimation is then incorporated into the proposed classification framework as a locality constraint to further enhance its discriminating power. Experimental results on six challenging 3D facial datasets show that the proposed KMTS–TPWCRC framework achieves promising results for human face recognition with missing parts, occlusions, data corruptions, expressions and pose variations

KW - face-recognition

KW - computer-vision

KW - image-processing

U2 - 10.1016/j.patcog.2015.09.035

DO - 10.1016/j.patcog.2015.09.035

M3 - Article

VL - 52

SP - 218

EP - 237

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 1

ER -