A blur-robust descriptor with applications to face recognition

Raghuraman Gopalan, Sima Taheri, Pavan Turaga, Rama Chellappa

Research output: Contribution to journalArticle

50 Citations (Scopus)

Abstract

Understanding the effect of blur is an important problem in unconstrained visual analysis. We address this problem in the context of image-based recognition by a fusion of image-formation models and differential geometric tools. First, we discuss the space spanned by blurred versions of an image and then, under certain assumptions, provide a differential geometric analysis of that space. More specifically, we create a subspace resulting from convolution of an image with a complete set of orthonormal basis functions of a prespecified maximum size (that can represent an arbitrary blur kernel within that size), and show that the corresponding subspaces created from a clean image and its blurred versions are equal under the ideal case of zero noise and some assumptions on the properties of blur kernels. We then study the practical utility of this subspace representation for the problem of direct recognition of blurred faces by viewing the subspaces as points on the Grassmann manifold and present methods to perform recognition for cases where the blur is both homogenous and spatially varying. We empirically analyze the effect of noise, as well as the presence of other facial variations between the gallery and probe images, and provide comparisons with existing approaches on standard data sets.

Original languageEnglish (US)
Article number6127874
Pages (from-to)1220-1226
Number of pages7
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume34
Issue number6
DOIs
StatePublished - 2012

Fingerprint

Face recognition
Face Recognition
Convolution
Descriptors
Image processing
Fusion reactions
Subspace
kernel
Grassmann Manifold
Geometric Analysis
Orthonormal basis
Basis Functions
Fusion
Probe
Face
Zero
Arbitrary

Keywords

  • Blur
  • Convolution
  • Face recognition.
  • Grassmann manifold
  • Subspace

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Software
  • Computational Theory and Mathematics
  • Applied Mathematics

Cite this

A blur-robust descriptor with applications to face recognition. / Gopalan, Raghuraman; Taheri, Sima; Turaga, Pavan; Chellappa, Rama.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34, No. 6, 6127874, 2012, p. 1220-1226.

Research output: Contribution to journalArticle

Gopalan, Raghuraman ; Taheri, Sima ; Turaga, Pavan ; Chellappa, Rama. / A blur-robust descriptor with applications to face recognition. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012 ; Vol. 34, No. 6. pp. 1220-1226.
@article{6f126cf5c0d044e78510d696df148938,
title = "A blur-robust descriptor with applications to face recognition",
abstract = "Understanding the effect of blur is an important problem in unconstrained visual analysis. We address this problem in the context of image-based recognition by a fusion of image-formation models and differential geometric tools. First, we discuss the space spanned by blurred versions of an image and then, under certain assumptions, provide a differential geometric analysis of that space. More specifically, we create a subspace resulting from convolution of an image with a complete set of orthonormal basis functions of a prespecified maximum size (that can represent an arbitrary blur kernel within that size), and show that the corresponding subspaces created from a clean image and its blurred versions are equal under the ideal case of zero noise and some assumptions on the properties of blur kernels. We then study the practical utility of this subspace representation for the problem of direct recognition of blurred faces by viewing the subspaces as points on the Grassmann manifold and present methods to perform recognition for cases where the blur is both homogenous and spatially varying. We empirically analyze the effect of noise, as well as the presence of other facial variations between the gallery and probe images, and provide comparisons with existing approaches on standard data sets.",
keywords = "Blur, Convolution, Face recognition., Grassmann manifold, Subspace",
author = "Raghuraman Gopalan and Sima Taheri and Pavan Turaga and Rama Chellappa",
year = "2012",
doi = "10.1109/TPAMI.2012.15",
language = "English (US)",
volume = "34",
pages = "1220--1226",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "6",

}

TY - JOUR

T1 - A blur-robust descriptor with applications to face recognition

AU - Gopalan, Raghuraman

AU - Taheri, Sima

AU - Turaga, Pavan

AU - Chellappa, Rama

PY - 2012

Y1 - 2012

N2 - Understanding the effect of blur is an important problem in unconstrained visual analysis. We address this problem in the context of image-based recognition by a fusion of image-formation models and differential geometric tools. First, we discuss the space spanned by blurred versions of an image and then, under certain assumptions, provide a differential geometric analysis of that space. More specifically, we create a subspace resulting from convolution of an image with a complete set of orthonormal basis functions of a prespecified maximum size (that can represent an arbitrary blur kernel within that size), and show that the corresponding subspaces created from a clean image and its blurred versions are equal under the ideal case of zero noise and some assumptions on the properties of blur kernels. We then study the practical utility of this subspace representation for the problem of direct recognition of blurred faces by viewing the subspaces as points on the Grassmann manifold and present methods to perform recognition for cases where the blur is both homogenous and spatially varying. We empirically analyze the effect of noise, as well as the presence of other facial variations between the gallery and probe images, and provide comparisons with existing approaches on standard data sets.

AB - Understanding the effect of blur is an important problem in unconstrained visual analysis. We address this problem in the context of image-based recognition by a fusion of image-formation models and differential geometric tools. First, we discuss the space spanned by blurred versions of an image and then, under certain assumptions, provide a differential geometric analysis of that space. More specifically, we create a subspace resulting from convolution of an image with a complete set of orthonormal basis functions of a prespecified maximum size (that can represent an arbitrary blur kernel within that size), and show that the corresponding subspaces created from a clean image and its blurred versions are equal under the ideal case of zero noise and some assumptions on the properties of blur kernels. We then study the practical utility of this subspace representation for the problem of direct recognition of blurred faces by viewing the subspaces as points on the Grassmann manifold and present methods to perform recognition for cases where the blur is both homogenous and spatially varying. We empirically analyze the effect of noise, as well as the presence of other facial variations between the gallery and probe images, and provide comparisons with existing approaches on standard data sets.

KW - Blur

KW - Convolution

KW - Face recognition.

KW - Grassmann manifold

KW - Subspace

UR - http://www.scopus.com/inward/record.url?scp=84860247150&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860247150&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2012.15

DO - 10.1109/TPAMI.2012.15

M3 - Article

C2 - 22231594

AN - SCOPUS:84860247150

VL - 34

SP - 1220

EP - 1226

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 6

M1 - 6127874

ER -