A novel convolutional neural network for facial expression recognition

Jing Li; Yang Mi; Jiahui Yu; Zhaojie Ju

doi:10.1007/978-981-13-7986-4_28

A novel convolutional neural network for facial expression recognition

Jing Li
, Yang Mi
, Jiahui Yu
, Zhaojie Ju

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

276 Downloads (Pure)

Abstract

Facial expression recognition is becoming a hot topic due to its wide applications in computer vision research fields. Traditional methods adopt hand-crafted features combined with classifiers to achieve the recognition goal. However, the accuracy of these methods often relies heavily on the extracted features and the classifier’s parameters, and thus cannot get good result with unseen data. Recently, deep learning, which simulates the mechanism of human brain to interpret data, has shown remarkable results in visual object recognition. In this paper, we present a novel convolutional neural network which consists of local binary patterns and improved Inception-ResNet layers for automatic facial expression recognition. We apply the proposed method to three expression datasets, i.e., the Extended Cohn-kanade Dataset (CK+), the Japanese Female Expression Database (JAFFE), and the FER2013 Dataset. The experimental results demonstrate the feasibility and effectiveness of our proposed network.

Original language	English
Title of host publication	ICCSIP 2018: Cognitive Systems and Signal Processing
Subtitle of host publication	4th International Conference, ICCSIP 2018, Beijing, China, November 29 - December 1, 2018, Revised Selected Papers, Part II
Editors	Fuchun Sun, Huaping Liu, Dewen Hu
Publisher	Springer
Chapter	28
Pages	310-320
Number of pages	11
ISBN (Print)	978-981-13-7985-7, 978-981-13-7986-4
DOIs	https://doi.org/10.1007/978-981-13-7986-4_28
Publication status	Published - 27 Apr 2019
Event	International Conference on Cognitive Systems and Information Processing - Beijing, China Duration: 24 Nov 2018 → 26 Nov 2018

Publication series

Name	Communications in Computer and InformationScience
Publisher	Springer
Volume	1006
ISSN (Print)	1865-0929

Conference

Conference	International Conference on Cognitive Systems and Information Processing
Abbreviated title	ICCSIP 2018
Country/Territory	China
City	Beijing
Period	24/11/18 → 26/11/18

Keywords

facial expression recognition
deep learning
LBP
inception-ResNet layers

Access to Document

10.1007/978-981-13-7986-4_28

ICCSIP_PostPrint
This is a post-peer-review, pre-copyedit version of an article published in ICCSIP 2018: Cognitive Systems and Signal Processing. 4th International Conference, ICCSIP 2018, Beijing, China, November 29 - December 1, 2018, Revised Selected Papers, Part II . The final authenticated version is available online at: http://dx.doi.org/10.1007/978-981-13-7986-4_28.
Accepted author manuscript (Post-print), 8.37 MB

Cite this

Li, J., Mi, Y., Yu, J., & Ju, Z. (2019). A novel convolutional neural network for facial expression recognition. In F. Sun, H. Liu, & D. Hu (Eds.), ICCSIP 2018: Cognitive Systems and Signal Processing: 4th International Conference, ICCSIP 2018, Beijing, China, November 29 - December 1, 2018, Revised Selected Papers, Part II (pp. 310-320). (Communications in Computer and InformationScience; Vol. 1006). Springer. https://doi.org/10.1007/978-981-13-7986-4_28

Li, Jing ; Mi, Yang ; Yu, Jiahui et al. / A novel convolutional neural network for facial expression recognition. ICCSIP 2018: Cognitive Systems and Signal Processing: 4th International Conference, ICCSIP 2018, Beijing, China, November 29 - December 1, 2018, Revised Selected Papers, Part II. editor / Fuchun Sun ; Huaping Liu ; Dewen Hu. Springer, 2019. pp. 310-320 (Communications in Computer and InformationScience).

@inproceedings{9909f44532284155ad7b7ea95c14daa3,

title = "A novel convolutional neural network for facial expression recognition",

abstract = "Facial expression recognition is becoming a hot topic due to its wide applications in computer vision research fields. Traditional methods adopt hand-crafted features combined with classifiers to achieve the recognition goal. However, the accuracy of these methods often relies heavily on the extracted features and the classifier{\textquoteright}s parameters, and thus cannot get good result with unseen data. Recently, deep learning, which simulates the mechanism of human brain to interpret data, has shown remarkable results in visual object recognition. In this paper, we present a novel convolutional neural network which consists of local binary patterns and improved Inception-ResNet layers for automatic facial expression recognition. We apply the proposed method to three expression datasets, i.e., the Extended Cohn-kanade Dataset (CK+), the Japanese Female Expression Database (JAFFE), and the FER2013 Dataset. The experimental results demonstrate the feasibility and effectiveness of our proposed network.",

keywords = "facial expression recognition, deep learning, LBP, inception-ResNet layers",

author = "Jing Li and Yang Mi and Jiahui Yu and Zhaojie Ju",

year = "2019",

month = apr,

day = "27",

doi = "10.1007/978-981-13-7986-4\_28",

language = "English",

isbn = "978-981-13-7985-7",

series = "Communications in Computer and InformationScience",

publisher = "Springer",

pages = "310--320",

editor = "Fuchun Sun and Huaping Liu and Dewen Hu",

booktitle = "ICCSIP 2018: Cognitive Systems and Signal Processing",

address = "Netherlands",

note = "International Conference on Cognitive Systems and Information Processing, ICCSIP 2018 ; Conference date: 24-11-2018 Through 26-11-2018",

}

Li, J, Mi, Y, Yu, J & Ju, Z 2019, A novel convolutional neural network for facial expression recognition. in F Sun, H Liu & D Hu (eds), ICCSIP 2018: Cognitive Systems and Signal Processing: 4th International Conference, ICCSIP 2018, Beijing, China, November 29 - December 1, 2018, Revised Selected Papers, Part II. Communications in Computer and InformationScience, vol. 1006, Springer, pp. 310-320, International Conference on Cognitive Systems and Information Processing, Beijing, China, 24/11/18. https://doi.org/10.1007/978-981-13-7986-4_28

A novel convolutional neural network for facial expression recognition. / Li, Jing; Mi, Yang; Yu, Jiahui et al.
ICCSIP 2018: Cognitive Systems and Signal Processing: 4th International Conference, ICCSIP 2018, Beijing, China, November 29 - December 1, 2018, Revised Selected Papers, Part II. ed. / Fuchun Sun; Huaping Liu; Dewen Hu. Springer, 2019. p. 310-320 (Communications in Computer and InformationScience; Vol. 1006).

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

TY - GEN

T1 - A novel convolutional neural network for facial expression recognition

AU - Li, Jing

AU - Mi, Yang

AU - Yu, Jiahui

AU - Ju, Zhaojie

PY - 2019/4/27

Y1 - 2019/4/27

N2 - Facial expression recognition is becoming a hot topic due to its wide applications in computer vision research fields. Traditional methods adopt hand-crafted features combined with classifiers to achieve the recognition goal. However, the accuracy of these methods often relies heavily on the extracted features and the classifier’s parameters, and thus cannot get good result with unseen data. Recently, deep learning, which simulates the mechanism of human brain to interpret data, has shown remarkable results in visual object recognition. In this paper, we present a novel convolutional neural network which consists of local binary patterns and improved Inception-ResNet layers for automatic facial expression recognition. We apply the proposed method to three expression datasets, i.e., the Extended Cohn-kanade Dataset (CK+), the Japanese Female Expression Database (JAFFE), and the FER2013 Dataset. The experimental results demonstrate the feasibility and effectiveness of our proposed network.

AB - Facial expression recognition is becoming a hot topic due to its wide applications in computer vision research fields. Traditional methods adopt hand-crafted features combined with classifiers to achieve the recognition goal. However, the accuracy of these methods often relies heavily on the extracted features and the classifier’s parameters, and thus cannot get good result with unseen data. Recently, deep learning, which simulates the mechanism of human brain to interpret data, has shown remarkable results in visual object recognition. In this paper, we present a novel convolutional neural network which consists of local binary patterns and improved Inception-ResNet layers for automatic facial expression recognition. We apply the proposed method to three expression datasets, i.e., the Extended Cohn-kanade Dataset (CK+), the Japanese Female Expression Database (JAFFE), and the FER2013 Dataset. The experimental results demonstrate the feasibility and effectiveness of our proposed network.

KW - facial expression recognition

KW - deep learning

KW - LBP

KW - inception-ResNet layers

UR - https://www.aconf.org/conf_158842.html

U2 - 10.1007/978-981-13-7986-4_28

DO - 10.1007/978-981-13-7986-4_28

M3 - Conference contribution

SN - 978-981-13-7985-7

SN - 978-981-13-7986-4

T3 - Communications in Computer and InformationScience

SP - 310

EP - 320

BT - ICCSIP 2018: Cognitive Systems and Signal Processing

A2 - Sun, Fuchun

A2 - Liu, Huaping

A2 - Hu, Dewen

PB - Springer

T2 - International Conference on Cognitive Systems and Information Processing

Y2 - 24 November 2018 through 26 November 2018

ER -

Li J, Mi Y, Yu J, Ju Z. A novel convolutional neural network for facial expression recognition. In Sun F, Liu H, Hu D, editors, ICCSIP 2018: Cognitive Systems and Signal Processing: 4th International Conference, ICCSIP 2018, Beijing, China, November 29 - December 1, 2018, Revised Selected Papers, Part II. Springer. 2019. p. 310-320. (Communications in Computer and InformationScience). doi: 10.1007/978-981-13-7986-4_28

A novel convolutional neural network for facial expression recognition

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this