Multiscale Feature Fusion for Face Identification

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

Over the past 20 years, information fusion has seen rapid development and has been used in many applications, including pattern recognition and computer vision. Multi-modal biometrics is one form of information fusion where biometric information from different modes of input (e.g., finger print, iris image, face image) is fused in order to achieve superior recognition performance. In this paper we propose a novel approach to multiscale information fusion for face identification where facial information from a single mode of input (i.e. a single image) at different spatial scales of focus is fused. We consider Local Binary Pattern (LBP) image descriptor, and carefully choose the LBP parameters to decide the spatial scale. Thus different values of the LBP parameters lead to LBP feature vectors at different spatial scales. These different LBP feature vectors are `fused' through an image distance function, which is then used for face image classification. We call this fusion method Multiscale Feature Fusion (MFF). Extensive experimentation has been conducted on the ORL, AR and FERET face image databases. Results show MFF does indeed produce superior classification performance when compared with the best results reported in the literature.
LanguageEnglish
DOIs
Publication statusPublished - 20 Jul 2017

Fingerprint

Information fusion
Biometrics
Image classification
Computer vision
Pattern recognition

Keywords

  • Face
  • Feature Extraction
  • Iris Recognition
  • Fuses
  • Image Representation
  • Histograms

Cite this

@conference{1d5b974963c84c50bce1e1b58eb4a29a,
title = "Multiscale Feature Fusion for Face Identification",
abstract = "Over the past 20 years, information fusion has seen rapid development and has been used in many applications, including pattern recognition and computer vision. Multi-modal biometrics is one form of information fusion where biometric information from different modes of input (e.g., finger print, iris image, face image) is fused in order to achieve superior recognition performance. In this paper we propose a novel approach to multiscale information fusion for face identification where facial information from a single mode of input (i.e. a single image) at different spatial scales of focus is fused. We consider Local Binary Pattern (LBP) image descriptor, and carefully choose the LBP parameters to decide the spatial scale. Thus different values of the LBP parameters lead to LBP feature vectors at different spatial scales. These different LBP feature vectors are `fused' through an image distance function, which is then used for face image classification. We call this fusion method Multiscale Feature Fusion (MFF). Extensive experimentation has been conducted on the ORL, AR and FERET face image databases. Results show MFF does indeed produce superior classification performance when compared with the best results reported in the literature.",
keywords = "Face, Feature Extraction, Iris Recognition, Fuses, Image Representation, Histograms",
author = "Xin Wei and Hui Wang and Huan Wan and Bryan Scotney",
note = "ISBN: 978-1-5386-2201-8",
year = "2017",
month = "7",
day = "20",
doi = "10.1109/CYBConf.2017.7985795",
language = "English",

}

TY - CONF

T1 - Multiscale Feature Fusion for Face Identification

AU - Wei, Xin

AU - Wang, Hui

AU - Wan, Huan

AU - Scotney, Bryan

N1 - ISBN: 978-1-5386-2201-8

PY - 2017/7/20

Y1 - 2017/7/20

N2 - Over the past 20 years, information fusion has seen rapid development and has been used in many applications, including pattern recognition and computer vision. Multi-modal biometrics is one form of information fusion where biometric information from different modes of input (e.g., finger print, iris image, face image) is fused in order to achieve superior recognition performance. In this paper we propose a novel approach to multiscale information fusion for face identification where facial information from a single mode of input (i.e. a single image) at different spatial scales of focus is fused. We consider Local Binary Pattern (LBP) image descriptor, and carefully choose the LBP parameters to decide the spatial scale. Thus different values of the LBP parameters lead to LBP feature vectors at different spatial scales. These different LBP feature vectors are `fused' through an image distance function, which is then used for face image classification. We call this fusion method Multiscale Feature Fusion (MFF). Extensive experimentation has been conducted on the ORL, AR and FERET face image databases. Results show MFF does indeed produce superior classification performance when compared with the best results reported in the literature.

AB - Over the past 20 years, information fusion has seen rapid development and has been used in many applications, including pattern recognition and computer vision. Multi-modal biometrics is one form of information fusion where biometric information from different modes of input (e.g., finger print, iris image, face image) is fused in order to achieve superior recognition performance. In this paper we propose a novel approach to multiscale information fusion for face identification where facial information from a single mode of input (i.e. a single image) at different spatial scales of focus is fused. We consider Local Binary Pattern (LBP) image descriptor, and carefully choose the LBP parameters to decide the spatial scale. Thus different values of the LBP parameters lead to LBP feature vectors at different spatial scales. These different LBP feature vectors are `fused' through an image distance function, which is then used for face image classification. We call this fusion method Multiscale Feature Fusion (MFF). Extensive experimentation has been conducted on the ORL, AR and FERET face image databases. Results show MFF does indeed produce superior classification performance when compared with the best results reported in the literature.

KW - Face

KW - Feature Extraction

KW - Iris Recognition

KW - Fuses

KW - Image Representation

KW - Histograms

UR - https://ieeexplore.ieee.org/abstract/document/7985795/

U2 - 10.1109/CYBConf.2017.7985795

DO - 10.1109/CYBConf.2017.7985795

M3 - Paper

ER -