Face recognition using scattering convolutional network

Shervin Minaee, Amirali Abdolrashidi, Yao Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Face recognition has been an active research area in the past few decades. In general, face recognition can be very challenging due to variations in viewpoint, illumination, facial expression, etc. Therefore it is essential to extract features which are invariant to some or all of these variations. Here a new image representation, called scattering trans-form/network, has been used to extract features from faces. The scattering transform is a kind of convolutional network which provides a powerful multi-layer representation for signals. After extraction of scattering features, PCA is applied to reduce the dimensionality of the data and then a multi-class support vector machine is used to perform recognition. The proposed algorithm has been tested on three face datasets and achieved a very high recognition rate.

Original languageEnglish (US)
Title of host publication2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
Volume2018-January
ISBN (Electronic)9781538648735
DOIs
StatePublished - Jan 12 2018
Event2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Philadelphia, United States
Duration: Dec 2 2017 → …

Other

Other2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017
CountryUnited States
CityPhiladelphia
Period12/2/17 → …

Fingerprint

Face recognition
Scattering
Passive Cutaneous Anaphylaxis
Facial Expression
Lighting
Support vector machines
Research
Facial Recognition
Support Vector Machine
Datasets

ASJC Scopus subject areas

  • Health Informatics
  • Clinical Neurology
  • Signal Processing
  • Cardiology and Cardiovascular Medicine

Cite this

Minaee, S., Abdolrashidi, A., & Wang, Y. (2018). Face recognition using scattering convolutional network. In 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings (Vol. 2018-January, pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SPMB.2017.8257025

Face recognition using scattering convolutional network. / Minaee, Shervin; Abdolrashidi, Amirali; Wang, Yao.

2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Minaee, S, Abdolrashidi, A & Wang, Y 2018, Face recognition using scattering convolutional network. in 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017, Philadelphia, United States, 12/2/17. https://doi.org/10.1109/SPMB.2017.8257025
Minaee S, Abdolrashidi A, Wang Y. Face recognition using scattering convolutional network. In 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6 https://doi.org/10.1109/SPMB.2017.8257025
Minaee, Shervin ; Abdolrashidi, Amirali ; Wang, Yao. / Face recognition using scattering convolutional network. 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6
@inproceedings{e923a378e1624a5289b0d5791007769f,
title = "Face recognition using scattering convolutional network",
abstract = "Face recognition has been an active research area in the past few decades. In general, face recognition can be very challenging due to variations in viewpoint, illumination, facial expression, etc. Therefore it is essential to extract features which are invariant to some or all of these variations. Here a new image representation, called scattering trans-form/network, has been used to extract features from faces. The scattering transform is a kind of convolutional network which provides a powerful multi-layer representation for signals. After extraction of scattering features, PCA is applied to reduce the dimensionality of the data and then a multi-class support vector machine is used to perform recognition. The proposed algorithm has been tested on three face datasets and achieved a very high recognition rate.",
author = "Shervin Minaee and Amirali Abdolrashidi and Yao Wang",
year = "2018",
month = "1",
day = "12",
doi = "10.1109/SPMB.2017.8257025",
language = "English (US)",
volume = "2018-January",
pages = "1--6",
booktitle = "2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Face recognition using scattering convolutional network

AU - Minaee, Shervin

AU - Abdolrashidi, Amirali

AU - Wang, Yao

PY - 2018/1/12

Y1 - 2018/1/12

N2 - Face recognition has been an active research area in the past few decades. In general, face recognition can be very challenging due to variations in viewpoint, illumination, facial expression, etc. Therefore it is essential to extract features which are invariant to some or all of these variations. Here a new image representation, called scattering trans-form/network, has been used to extract features from faces. The scattering transform is a kind of convolutional network which provides a powerful multi-layer representation for signals. After extraction of scattering features, PCA is applied to reduce the dimensionality of the data and then a multi-class support vector machine is used to perform recognition. The proposed algorithm has been tested on three face datasets and achieved a very high recognition rate.

AB - Face recognition has been an active research area in the past few decades. In general, face recognition can be very challenging due to variations in viewpoint, illumination, facial expression, etc. Therefore it is essential to extract features which are invariant to some or all of these variations. Here a new image representation, called scattering trans-form/network, has been used to extract features from faces. The scattering transform is a kind of convolutional network which provides a powerful multi-layer representation for signals. After extraction of scattering features, PCA is applied to reduce the dimensionality of the data and then a multi-class support vector machine is used to perform recognition. The proposed algorithm has been tested on three face datasets and achieved a very high recognition rate.

UR - http://www.scopus.com/inward/record.url?scp=85050656188&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050656188&partnerID=8YFLogxK

U2 - 10.1109/SPMB.2017.8257025

DO - 10.1109/SPMB.2017.8257025

M3 - Conference contribution

AN - SCOPUS:85050656188

VL - 2018-January

SP - 1

EP - 6

BT - 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -