Realtime training on mobile devices for face recognition applications

Kwontaeg Choi, Kar Ann Toh, Hyeran Byun

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

Due to the increases in processing power and storage capacity of mobile devices over the years, an incorporation of realtime face recognition to mobile devices is no longer unattainable. However, the possibility of the realtime learning of a large number of samples within mobile devices must be established. In this paper, we attempt to establish this possibility by presenting a realtime training algorithm in mobile devices for face recognition related applications. This is differentiated from those traditional algorithms which focused on realtime classification. In order to solve the challenging realtime issue in mobile devices, we extract local face features using some local random bases and then a sequential neural network is trained incrementally with these features. We demonstrate the effectiveness of the proposed algorithm and the feasibility of its application in mobile devices through empirical experiments. Our results show that the proposed algorithm significantly outperforms several popular face recognition methods with a dramatic reduction in computational speed. Moreover, only the proposed method shows the ability to train additional samples incrementally in realtime without memory failure and accuracy degradation using a recent mobile phone model.

Original languageEnglish
Pages (from-to)386-400
Number of pages15
JournalPattern Recognition
Volume44
Issue number2
DOIs
Publication statusPublished - 2011 Feb 1

Fingerprint

Face recognition
Mobile devices
Mobile phones
Neural networks
Data storage equipment
Degradation
Processing
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{1cb9191461e04102a73bd08bf1c897bd,
title = "Realtime training on mobile devices for face recognition applications",
abstract = "Due to the increases in processing power and storage capacity of mobile devices over the years, an incorporation of realtime face recognition to mobile devices is no longer unattainable. However, the possibility of the realtime learning of a large number of samples within mobile devices must be established. In this paper, we attempt to establish this possibility by presenting a realtime training algorithm in mobile devices for face recognition related applications. This is differentiated from those traditional algorithms which focused on realtime classification. In order to solve the challenging realtime issue in mobile devices, we extract local face features using some local random bases and then a sequential neural network is trained incrementally with these features. We demonstrate the effectiveness of the proposed algorithm and the feasibility of its application in mobile devices through empirical experiments. Our results show that the proposed algorithm significantly outperforms several popular face recognition methods with a dramatic reduction in computational speed. Moreover, only the proposed method shows the ability to train additional samples incrementally in realtime without memory failure and accuracy degradation using a recent mobile phone model.",
author = "Kwontaeg Choi and Toh, {Kar Ann} and Hyeran Byun",
year = "2011",
month = "2",
day = "1",
doi = "10.1016/j.patcog.2010.08.009",
language = "English",
volume = "44",
pages = "386--400",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "2",

}

Realtime training on mobile devices for face recognition applications. / Choi, Kwontaeg; Toh, Kar Ann; Byun, Hyeran.

In: Pattern Recognition, Vol. 44, No. 2, 01.02.2011, p. 386-400.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Realtime training on mobile devices for face recognition applications

AU - Choi, Kwontaeg

AU - Toh, Kar Ann

AU - Byun, Hyeran

PY - 2011/2/1

Y1 - 2011/2/1

N2 - Due to the increases in processing power and storage capacity of mobile devices over the years, an incorporation of realtime face recognition to mobile devices is no longer unattainable. However, the possibility of the realtime learning of a large number of samples within mobile devices must be established. In this paper, we attempt to establish this possibility by presenting a realtime training algorithm in mobile devices for face recognition related applications. This is differentiated from those traditional algorithms which focused on realtime classification. In order to solve the challenging realtime issue in mobile devices, we extract local face features using some local random bases and then a sequential neural network is trained incrementally with these features. We demonstrate the effectiveness of the proposed algorithm and the feasibility of its application in mobile devices through empirical experiments. Our results show that the proposed algorithm significantly outperforms several popular face recognition methods with a dramatic reduction in computational speed. Moreover, only the proposed method shows the ability to train additional samples incrementally in realtime without memory failure and accuracy degradation using a recent mobile phone model.

AB - Due to the increases in processing power and storage capacity of mobile devices over the years, an incorporation of realtime face recognition to mobile devices is no longer unattainable. However, the possibility of the realtime learning of a large number of samples within mobile devices must be established. In this paper, we attempt to establish this possibility by presenting a realtime training algorithm in mobile devices for face recognition related applications. This is differentiated from those traditional algorithms which focused on realtime classification. In order to solve the challenging realtime issue in mobile devices, we extract local face features using some local random bases and then a sequential neural network is trained incrementally with these features. We demonstrate the effectiveness of the proposed algorithm and the feasibility of its application in mobile devices through empirical experiments. Our results show that the proposed algorithm significantly outperforms several popular face recognition methods with a dramatic reduction in computational speed. Moreover, only the proposed method shows the ability to train additional samples incrementally in realtime without memory failure and accuracy degradation using a recent mobile phone model.

UR - http://www.scopus.com/inward/record.url?scp=77957979158&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957979158&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2010.08.009

DO - 10.1016/j.patcog.2010.08.009

M3 - Article

VL - 44

SP - 386

EP - 400

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 2

ER -