Face representation and recognition with local curvelet patterns

Wei Zhou, Alireza Ahrary, Seiichiro Kamata

Research output: Contribution to journalArticle

Abstract

In this paper, we propose Local Curvelet Binary Patterns (LCBP) and Learned Local Curvelet Patterns (LLCP) for presenting the local features of facial images. The proposed methods are based on Curvelet transform which can overcome the weakness of traditional Gabor wavelets in higher dimensions, and better capture the curve singularities and hyperplane singularities of facial images. LCBP can be regarded as a combination of Curvelet features and LBP operator while LLCP designs several learned codebooks from patch sets, which are constructed by sampling patches from Curvelet filtered facial images. Each facial image can be encoded into multiple pattern maps and block-based histograms of these patterns are concatenated into an histogram sequence to be used as a face descriptor. During the face representation phase, one input patch is encoded by one pattern in LCBP while multi-patterns in LLCP. Finally, an effective classifier called Weighted Histogram Spatially constrained Earth Mover's Distance (WHSEMD) which utilizes the discriminative powers of different facial parts, the different patterns and the spatial information of face is proposed. Performance assessment in face recognition and gender estimation under different challenges shows that the proposed approaches are superior than traditional ones.

Original languageEnglish
Pages (from-to)3078-3087
Number of pages10
JournalIEICE Transactions on Information and Systems
VolumeE95-D
Issue number12
DOIs
Publication statusPublished - 2012 Dec

Fingerprint

Face recognition
Classifiers
Earth (planet)
Sampling

Keywords

  • Face recognition
  • Gender estimation
  • Learned local curvelet patterns
  • Local curvelet binary patterns
  • WHSEMD

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

Face representation and recognition with local curvelet patterns. / Zhou, Wei; Ahrary, Alireza; Kamata, Seiichiro.

In: IEICE Transactions on Information and Systems, Vol. E95-D, No. 12, 12.2012, p. 3078-3087.

Research output: Contribution to journalArticle

@article{479baf164a1845209f2fd5f5cd214b1a,
title = "Face representation and recognition with local curvelet patterns",
abstract = "In this paper, we propose Local Curvelet Binary Patterns (LCBP) and Learned Local Curvelet Patterns (LLCP) for presenting the local features of facial images. The proposed methods are based on Curvelet transform which can overcome the weakness of traditional Gabor wavelets in higher dimensions, and better capture the curve singularities and hyperplane singularities of facial images. LCBP can be regarded as a combination of Curvelet features and LBP operator while LLCP designs several learned codebooks from patch sets, which are constructed by sampling patches from Curvelet filtered facial images. Each facial image can be encoded into multiple pattern maps and block-based histograms of these patterns are concatenated into an histogram sequence to be used as a face descriptor. During the face representation phase, one input patch is encoded by one pattern in LCBP while multi-patterns in LLCP. Finally, an effective classifier called Weighted Histogram Spatially constrained Earth Mover's Distance (WHSEMD) which utilizes the discriminative powers of different facial parts, the different patterns and the spatial information of face is proposed. Performance assessment in face recognition and gender estimation under different challenges shows that the proposed approaches are superior than traditional ones.",
keywords = "Face recognition, Gender estimation, Learned local curvelet patterns, Local curvelet binary patterns, WHSEMD",
author = "Wei Zhou and Alireza Ahrary and Seiichiro Kamata",
year = "2012",
month = "12",
doi = "10.1587/transinf.E95.D.3078",
language = "English",
volume = "E95-D",
pages = "3078--3087",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "12",

}

TY - JOUR

T1 - Face representation and recognition with local curvelet patterns

AU - Zhou, Wei

AU - Ahrary, Alireza

AU - Kamata, Seiichiro

PY - 2012/12

Y1 - 2012/12

N2 - In this paper, we propose Local Curvelet Binary Patterns (LCBP) and Learned Local Curvelet Patterns (LLCP) for presenting the local features of facial images. The proposed methods are based on Curvelet transform which can overcome the weakness of traditional Gabor wavelets in higher dimensions, and better capture the curve singularities and hyperplane singularities of facial images. LCBP can be regarded as a combination of Curvelet features and LBP operator while LLCP designs several learned codebooks from patch sets, which are constructed by sampling patches from Curvelet filtered facial images. Each facial image can be encoded into multiple pattern maps and block-based histograms of these patterns are concatenated into an histogram sequence to be used as a face descriptor. During the face representation phase, one input patch is encoded by one pattern in LCBP while multi-patterns in LLCP. Finally, an effective classifier called Weighted Histogram Spatially constrained Earth Mover's Distance (WHSEMD) which utilizes the discriminative powers of different facial parts, the different patterns and the spatial information of face is proposed. Performance assessment in face recognition and gender estimation under different challenges shows that the proposed approaches are superior than traditional ones.

AB - In this paper, we propose Local Curvelet Binary Patterns (LCBP) and Learned Local Curvelet Patterns (LLCP) for presenting the local features of facial images. The proposed methods are based on Curvelet transform which can overcome the weakness of traditional Gabor wavelets in higher dimensions, and better capture the curve singularities and hyperplane singularities of facial images. LCBP can be regarded as a combination of Curvelet features and LBP operator while LLCP designs several learned codebooks from patch sets, which are constructed by sampling patches from Curvelet filtered facial images. Each facial image can be encoded into multiple pattern maps and block-based histograms of these patterns are concatenated into an histogram sequence to be used as a face descriptor. During the face representation phase, one input patch is encoded by one pattern in LCBP while multi-patterns in LLCP. Finally, an effective classifier called Weighted Histogram Spatially constrained Earth Mover's Distance (WHSEMD) which utilizes the discriminative powers of different facial parts, the different patterns and the spatial information of face is proposed. Performance assessment in face recognition and gender estimation under different challenges shows that the proposed approaches are superior than traditional ones.

KW - Face recognition

KW - Gender estimation

KW - Learned local curvelet patterns

KW - Local curvelet binary patterns

KW - WHSEMD

UR - http://www.scopus.com/inward/record.url?scp=84870655997&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870655997&partnerID=8YFLogxK

U2 - 10.1587/transinf.E95.D.3078

DO - 10.1587/transinf.E95.D.3078

M3 - Article

AN - SCOPUS:84870655997

VL - E95-D

SP - 3078

EP - 3087

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 12

ER -