A cascaded convolutional neural network for age estimation of unconstrained faces

Jun Cheng Chen; Amit Kumar; Rajeev Ranjan; Vishal M. Patel; Azadeh Alavi; Rama Chellappa

doi:10.1109/BTAS.2016.7791154

A cascaded convolutional neural network for age estimation of unconstrained faces

Jun Cheng Chen
, Amit Kumar
, Rajeev Ranjan
, Vishal M. Patel
, Azadeh Alavi
, Rama Chellappa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We propose a coarse-to-fine approach for estimating the apparent age from unconstrained face images using deep convolutional neural networks (DCNNs). The proposed method consists of three modules. The first one is a DCNN-based age group classifier which classifies a given face image into age groups. The second module is a collection of DCNN-based regressors which compute the fine-grained age estimate corresponding in each age class. Finally, any erroneous age prediction is corrected using an error-correcting mechanism. Experimental evaluations on three publicly available datasets for age estimation show that the proposed approach is able to reliably estimate the age; in addition, the coarse-to-fine strategy and the error correction module significantly improve the performance.

Original language	English (US)
Title of host publication	2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467397339
DOIs	https://doi.org/10.1109/BTAS.2016.7791154
State	Published - Dec 19 2016
Externally published	Yes
Event	8th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2016 - Niagara Falls, United States Duration: Sep 6 2016 → Sep 9 2016

Publication series

Name	2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016

Conference

Conference	8th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2016
Country/Territory	United States
City	Niagara Falls
Period	9/6/16 → 9/9/16

ASJC Scopus subject areas

Statistics and Probability
Biomedical Engineering
Computer Science Applications

Access to Document

10.1109/BTAS.2016.7791154

Cite this

Chen, J. C., Kumar, A., Ranjan, R., Patel, V. M., Alavi, A., & Chellappa, R. (2016). A cascaded convolutional neural network for age estimation of unconstrained faces. In 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016 Article 7791154 (2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BTAS.2016.7791154

A cascaded convolutional neural network for age estimation of unconstrained faces. / Chen, Jun Cheng; Kumar, Amit; Ranjan, Rajeev et al.
2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7791154 (2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chen, JC, Kumar, A, Ranjan, R, Patel, VM, Alavi, A & Chellappa, R 2016, A cascaded convolutional neural network for age estimation of unconstrained faces. in 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016., 7791154, 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016, Institute of Electrical and Electronics Engineers Inc., 8th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2016, Niagara Falls, United States, 9/6/16. https://doi.org/10.1109/BTAS.2016.7791154

Chen JC, Kumar A, Ranjan R, Patel VM, Alavi A, Chellappa R. A cascaded convolutional neural network for age estimation of unconstrained faces. In 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 7791154. (2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016). doi: 10.1109/BTAS.2016.7791154

Chen, Jun Cheng ; Kumar, Amit ; Ranjan, Rajeev et al. / A cascaded convolutional neural network for age estimation of unconstrained faces. 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. (2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016).

@inproceedings{3d709c0aef63464e9dda9d38be96f287,

title = "A cascaded convolutional neural network for age estimation of unconstrained faces",

abstract = "We propose a coarse-to-fine approach for estimating the apparent age from unconstrained face images using deep convolutional neural networks (DCNNs). The proposed method consists of three modules. The first one is a DCNN-based age group classifier which classifies a given face image into age groups. The second module is a collection of DCNN-based regressors which compute the fine-grained age estimate corresponding in each age class. Finally, any erroneous age prediction is corrected using an error-correcting mechanism. Experimental evaluations on three publicly available datasets for age estimation show that the proposed approach is able to reliably estimate the age; in addition, the coarse-to-fine strategy and the error correction module significantly improve the performance.",

author = "Chen, \{Jun Cheng\} and Amit Kumar and Rajeev Ranjan and Patel, \{Vishal M.\} and Azadeh Alavi and Rama Chellappa",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 8th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2016 ; Conference date: 06-09-2016 Through 09-09-2016",

year = "2016",

month = dec,

day = "19",

doi = "10.1109/BTAS.2016.7791154",

language = "English (US)",

series = "2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016",

}

TY - GEN

T1 - A cascaded convolutional neural network for age estimation of unconstrained faces

AU - Chen, Jun Cheng

AU - Kumar, Amit

AU - Ranjan, Rajeev

AU - Patel, Vishal M.

AU - Alavi, Azadeh

AU - Chellappa, Rama

PY - 2016/12/19

Y1 - 2016/12/19

N2 - We propose a coarse-to-fine approach for estimating the apparent age from unconstrained face images using deep convolutional neural networks (DCNNs). The proposed method consists of three modules. The first one is a DCNN-based age group classifier which classifies a given face image into age groups. The second module is a collection of DCNN-based regressors which compute the fine-grained age estimate corresponding in each age class. Finally, any erroneous age prediction is corrected using an error-correcting mechanism. Experimental evaluations on three publicly available datasets for age estimation show that the proposed approach is able to reliably estimate the age; in addition, the coarse-to-fine strategy and the error correction module significantly improve the performance.

AB - We propose a coarse-to-fine approach for estimating the apparent age from unconstrained face images using deep convolutional neural networks (DCNNs). The proposed method consists of three modules. The first one is a DCNN-based age group classifier which classifies a given face image into age groups. The second module is a collection of DCNN-based regressors which compute the fine-grained age estimate corresponding in each age class. Finally, any erroneous age prediction is corrected using an error-correcting mechanism. Experimental evaluations on three publicly available datasets for age estimation show that the proposed approach is able to reliably estimate the age; in addition, the coarse-to-fine strategy and the error correction module significantly improve the performance.

UR - https://www.scopus.com/pages/publications/85011277914

UR - https://www.scopus.com/pages/publications/85011277914#tab=citedBy

U2 - 10.1109/BTAS.2016.7791154

DO - 10.1109/BTAS.2016.7791154

M3 - Conference contribution

AN - SCOPUS:85011277914

T3 - 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016

BT - 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2016

Y2 - 6 September 2016 through 9 September 2016

ER -

A cascaded convolutional neural network for age estimation of unconstrained faces

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this