Kernel ELM and CNN Based Facial Age Estimation

Furkan Gurpinar; Heysem Kaya; Hamdi Dibeklioglu; Albert Ali Salah

doi:10.1109/CVPRW.2016.103

Kernel ELM and CNN Based Facial Age Estimation

Furkan Gurpinar, Heysem Kaya, Hamdi Dibeklioglu, Albert Ali Salah

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

We propose a two-level system for apparent age estimation from facial images. Our system first classifies samples into overlapping age groups. Within each group, the apparent age is estimated with local regressors, whose outputs are then fused for the final estimate. We use a deformable parts model based face detector, and features from a pretrained deep convolutional network. Kernel extreme learning machines are used for classification. We evaluate our system on the ChaLearn Looking at People 2016 - Apparent Age Estimation challenge dataset, and report 0.3740 normal score on the sequestered test set.

Original language	English
Title of host publication	Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
Publisher	IEEE
Pages	785-791
Number of pages	7
ISBN (Electronic)	9781467388504
DOIs	https://doi.org/10.1109/CVPRW.2016.103
Publication status	Published - 16 Dec 2016
Event	29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 - Las Vegas, United States Duration: 26 Jun 2016 → 1 Jul 2016

Conference

Conference	29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
Country/Territory	United States
City	Las Vegas
Period	26/06/16 → 1/07/16

Access to Document

10.1109/CVPRW.2016.103

Cite this

@inproceedings{ad881727d23045eda5920a38c66bf0df,

title = "Kernel ELM and CNN Based Facial Age Estimation",

abstract = "We propose a two-level system for apparent age estimation from facial images. Our system first classifies samples into overlapping age groups. Within each group, the apparent age is estimated with local regressors, whose outputs are then fused for the final estimate. We use a deformable parts model based face detector, and features from a pretrained deep convolutional network. Kernel extreme learning machines are used for classification. We evaluate our system on the ChaLearn Looking at People 2016 - Apparent Age Estimation challenge dataset, and report 0.3740 normal score on the sequestered test set.",

author = "Furkan Gurpinar and Heysem Kaya and Hamdi Dibeklioglu and Salah, {Albert Ali}",

year = "2016",

month = dec,

day = "16",

doi = "10.1109/CVPRW.2016.103",

language = "English",

pages = "785--791",

booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016",

publisher = "IEEE",

address = "United States",

note = "29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 ; Conference date: 26-06-2016 Through 01-07-2016",

}

Gurpinar, F, Kaya, H, Dibeklioglu, H & Salah, AA 2016, Kernel ELM and CNN Based Facial Age Estimation. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016., 7789593, IEEE, pp. 785-791, 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016, Las Vegas, United States, 26/06/16. https://doi.org/10.1109/CVPRW.2016.103

TY - GEN

T1 - Kernel ELM and CNN Based Facial Age Estimation

AU - Gurpinar, Furkan

AU - Kaya, Heysem

AU - Dibeklioglu, Hamdi

AU - Salah, Albert Ali

PY - 2016/12/16

Y1 - 2016/12/16

N2 - We propose a two-level system for apparent age estimation from facial images. Our system first classifies samples into overlapping age groups. Within each group, the apparent age is estimated with local regressors, whose outputs are then fused for the final estimate. We use a deformable parts model based face detector, and features from a pretrained deep convolutional network. Kernel extreme learning machines are used for classification. We evaluate our system on the ChaLearn Looking at People 2016 - Apparent Age Estimation challenge dataset, and report 0.3740 normal score on the sequestered test set.

AB - We propose a two-level system for apparent age estimation from facial images. Our system first classifies samples into overlapping age groups. Within each group, the apparent age is estimated with local regressors, whose outputs are then fused for the final estimate. We use a deformable parts model based face detector, and features from a pretrained deep convolutional network. Kernel extreme learning machines are used for classification. We evaluate our system on the ChaLearn Looking at People 2016 - Apparent Age Estimation challenge dataset, and report 0.3740 normal score on the sequestered test set.

UR - http://www.scopus.com/inward/record.url?scp=85010203580&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2016.103

DO - 10.1109/CVPRW.2016.103

M3 - Conference contribution

AN - SCOPUS:85010203580

SP - 785

EP - 791

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016

PB - IEEE

T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016

Y2 - 26 June 2016 through 1 July 2016

ER -

Kernel ELM and CNN Based Facial Age Estimation

Abstract

Conference

Access to Document

Fingerprint

Cite this