Efficient location, imaging and recognition of faces by single-pixel camera

Wojciech Roga, John Jeffers

Research output: Contribution to journalArticle

Abstract

Face recognition is a problem with many practical applications. Modern image analysis methods such as object tracking, feature extraction, classification or verification that explore advanced techniques of machine learning and compressive sensing have been used for this purpose. Many of these methods, which are usually applied in image post-processing, are adaptable to fast intelligent viewing with a single-pixel camera. We study such a camera in the context of face recognition with limited information. We seek the optimal basis of patterns for the camera as well as to resolve practical issues related to face localisation and alignment. We compare the use of the Hadamard and eigenface bases for imaging and verification of faces. For the latter task we develop a simple algorithm based on compressive sensing.
LanguageEnglish
Pages1-13
Number of pages13
JournalJournal of Optics
Early online date2 Nov 2018
DOIs
Publication statusE-pub ahead of print - 2 Nov 2018

Fingerprint

Pixels
Cameras
pixels
cameras
Face recognition
Imaging techniques
machine learning
image analysis
pattern recognition
Image analysis
Learning systems
Feature extraction
alignment
Processing

Keywords

  • single-pixel camera
  • image analysis
  • face recognition

Cite this

@article{bfbd2d11ea5b4685af0a285b44a60462,
title = "Efficient location, imaging and recognition of faces by single-pixel camera",
abstract = "Face recognition is a problem with many practical applications. Modern image analysis methods such as object tracking, feature extraction, classification or verification that explore advanced techniques of machine learning and compressive sensing have been used for this purpose. Many of these methods, which are usually applied in image post-processing, are adaptable to fast intelligent viewing with a single-pixel camera. We study such a camera in the context of face recognition with limited information. We seek the optimal basis of patterns for the camera as well as to resolve practical issues related to face localisation and alignment. We compare the use of the Hadamard and eigenface bases for imaging and verification of faces. For the latter task we develop a simple algorithm based on compressive sensing.",
keywords = "single-pixel camera, image analysis, face recognition",
author = "Wojciech Roga and John Jeffers",
note = "This is an author-created, un-copyedited version of an article accepted for publication in Journal of Optics. IOP Publishing Ltd is not responsible for any errors or omissions in this version of the manuscript or any version derived from it. The Version of Record is available online at http://iopscience.iop.org/journal/2040-8986.",
year = "2018",
month = "11",
day = "2",
doi = "10.1088/2040-8986/aae7b9",
language = "English",
pages = "1--13",
journal = "Journal of Optics",
issn = "0972-8821",

}

Efficient location, imaging and recognition of faces by single-pixel camera. / Roga, Wojciech; Jeffers, John.

In: Journal of Optics, 02.11.2018, p. 1-13.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Efficient location, imaging and recognition of faces by single-pixel camera

AU - Roga, Wojciech

AU - Jeffers, John

N1 - This is an author-created, un-copyedited version of an article accepted for publication in Journal of Optics. IOP Publishing Ltd is not responsible for any errors or omissions in this version of the manuscript or any version derived from it. The Version of Record is available online at http://iopscience.iop.org/journal/2040-8986.

PY - 2018/11/2

Y1 - 2018/11/2

N2 - Face recognition is a problem with many practical applications. Modern image analysis methods such as object tracking, feature extraction, classification or verification that explore advanced techniques of machine learning and compressive sensing have been used for this purpose. Many of these methods, which are usually applied in image post-processing, are adaptable to fast intelligent viewing with a single-pixel camera. We study such a camera in the context of face recognition with limited information. We seek the optimal basis of patterns for the camera as well as to resolve practical issues related to face localisation and alignment. We compare the use of the Hadamard and eigenface bases for imaging and verification of faces. For the latter task we develop a simple algorithm based on compressive sensing.

AB - Face recognition is a problem with many practical applications. Modern image analysis methods such as object tracking, feature extraction, classification or verification that explore advanced techniques of machine learning and compressive sensing have been used for this purpose. Many of these methods, which are usually applied in image post-processing, are adaptable to fast intelligent viewing with a single-pixel camera. We study such a camera in the context of face recognition with limited information. We seek the optimal basis of patterns for the camera as well as to resolve practical issues related to face localisation and alignment. We compare the use of the Hadamard and eigenface bases for imaging and verification of faces. For the latter task we develop a simple algorithm based on compressive sensing.

KW - single-pixel camera

KW - image analysis

KW - face recognition

UR - http://iopscience.iop.org/journal/2040-8986

U2 - 10.1088/2040-8986/aae7b9

DO - 10.1088/2040-8986/aae7b9

M3 - Article

SP - 1

EP - 13

JO - Journal of Optics

T2 - Journal of Optics

JF - Journal of Optics

SN - 0972-8821

ER -