Towards a robust face recognition system using compressive sensing

Allen Y. Yang, Zihan Zhou, Yi Ma, S. Shankar Sastry

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

An application of compressive sensing (CS) theory in image-based robust face recognition is considered. Most contemporary face recognition systems suffer from limited abilities to handle image nuisances such as illumination, facial disguise, and pose misalignment. Motivated by CS, the problem has been recently cast in a sparse representation framework: The sparsest linear combination of a query image is sought using all prior training images as an overcomplete dictionary, and the dominant sparse coefficients reveal the identity of the query image. The ability to perform dense error correction directly in the image space also provides an intriguing solution to compensate pixel corruption and improve the recognition accuracy exceeding most existing solutions. Furthermore, a local iterative process can be applied to solve for an image transformation applied to the face region when the query image is misaligned. Finally, we discuss the state of the art in fast ℓ 1 -minimization to improve the speed of the robust face recognition system. The paper also provides useful guidelines to practitioners working in similar fields, such as acoustic/speech recognition.

Original languageEnglish (US)
Pages2250-2253
Number of pages4
StatePublished - Dec 1 2010
Event11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 - Makuhari, Chiba, Japan
Duration: Sep 26 2010Sep 30 2010

Conference

Conference11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010
CountryJapan
CityMakuhari, Chiba
Period9/26/109/30/10

Fingerprint

Speech Acoustics
Lighting
Guidelines
Facial Recognition
Face Recognition

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Speech and Hearing

Cite this

Yang, A. Y., Zhou, Z., Ma, Y., & Sastry, S. S. (2010). Towards a robust face recognition system using compressive sensing. 2250-2253. Paper presented at 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, Makuhari, Chiba, Japan.
Yang, Allen Y. ; Zhou, Zihan ; Ma, Yi ; Sastry, S. Shankar. / Towards a robust face recognition system using compressive sensing. Paper presented at 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, Makuhari, Chiba, Japan.4 p.
@conference{6cfedf3338b64c598377afe8c656cfb3,
title = "Towards a robust face recognition system using compressive sensing",
abstract = "An application of compressive sensing (CS) theory in image-based robust face recognition is considered. Most contemporary face recognition systems suffer from limited abilities to handle image nuisances such as illumination, facial disguise, and pose misalignment. Motivated by CS, the problem has been recently cast in a sparse representation framework: The sparsest linear combination of a query image is sought using all prior training images as an overcomplete dictionary, and the dominant sparse coefficients reveal the identity of the query image. The ability to perform dense error correction directly in the image space also provides an intriguing solution to compensate pixel corruption and improve the recognition accuracy exceeding most existing solutions. Furthermore, a local iterative process can be applied to solve for an image transformation applied to the face region when the query image is misaligned. Finally, we discuss the state of the art in fast ℓ 1 -minimization to improve the speed of the robust face recognition system. The paper also provides useful guidelines to practitioners working in similar fields, such as acoustic/speech recognition.",
author = "Yang, {Allen Y.} and Zihan Zhou and Yi Ma and Sastry, {S. Shankar}",
year = "2010",
month = "12",
day = "1",
language = "English (US)",
pages = "2250--2253",
note = "11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 ; Conference date: 26-09-2010 Through 30-09-2010",

}

Yang, AY, Zhou, Z, Ma, Y & Sastry, SS 2010, 'Towards a robust face recognition system using compressive sensing' Paper presented at 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, Makuhari, Chiba, Japan, 9/26/10 - 9/30/10, pp. 2250-2253.

Towards a robust face recognition system using compressive sensing. / Yang, Allen Y.; Zhou, Zihan; Ma, Yi; Sastry, S. Shankar.

2010. 2250-2253 Paper presented at 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, Makuhari, Chiba, Japan.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Towards a robust face recognition system using compressive sensing

AU - Yang, Allen Y.

AU - Zhou, Zihan

AU - Ma, Yi

AU - Sastry, S. Shankar

PY - 2010/12/1

Y1 - 2010/12/1

N2 - An application of compressive sensing (CS) theory in image-based robust face recognition is considered. Most contemporary face recognition systems suffer from limited abilities to handle image nuisances such as illumination, facial disguise, and pose misalignment. Motivated by CS, the problem has been recently cast in a sparse representation framework: The sparsest linear combination of a query image is sought using all prior training images as an overcomplete dictionary, and the dominant sparse coefficients reveal the identity of the query image. The ability to perform dense error correction directly in the image space also provides an intriguing solution to compensate pixel corruption and improve the recognition accuracy exceeding most existing solutions. Furthermore, a local iterative process can be applied to solve for an image transformation applied to the face region when the query image is misaligned. Finally, we discuss the state of the art in fast ℓ 1 -minimization to improve the speed of the robust face recognition system. The paper also provides useful guidelines to practitioners working in similar fields, such as acoustic/speech recognition.

AB - An application of compressive sensing (CS) theory in image-based robust face recognition is considered. Most contemporary face recognition systems suffer from limited abilities to handle image nuisances such as illumination, facial disguise, and pose misalignment. Motivated by CS, the problem has been recently cast in a sparse representation framework: The sparsest linear combination of a query image is sought using all prior training images as an overcomplete dictionary, and the dominant sparse coefficients reveal the identity of the query image. The ability to perform dense error correction directly in the image space also provides an intriguing solution to compensate pixel corruption and improve the recognition accuracy exceeding most existing solutions. Furthermore, a local iterative process can be applied to solve for an image transformation applied to the face region when the query image is misaligned. Finally, we discuss the state of the art in fast ℓ 1 -minimization to improve the speed of the robust face recognition system. The paper also provides useful guidelines to practitioners working in similar fields, such as acoustic/speech recognition.

UR - http://www.scopus.com/inward/record.url?scp=79959820342&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959820342&partnerID=8YFLogxK

M3 - Paper

SP - 2250

EP - 2253

ER -

Yang AY, Zhou Z, Ma Y, Sastry SS. Towards a robust face recognition system using compressive sensing. 2010. Paper presented at 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, Makuhari, Chiba, Japan.