Real-Time facial expression recognition based on cnn

Keng Cheng Liu, Chen Chien Hsu, Wei Yen Wang, Hsin Han Chiang

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

Abstract

In this paper, we propose a method for improving the robustness of real-Time facial expression recognition. Although there are many ways to improve the accuracy of facial expression recognition, a revamp of the training framework and image preprocessing allow better results in applications. One existing problem is that when the camera is capturing images in high speed, changes in image characteristics may occur at certain moments due to the influence of light and other factors. Such changes can result in incorrect recognition of the human facial expression. To solve this problem for smooth system operation and maintenance of recognition speed, we take changes in image characteristics at high speed capturing into account. The proposed method does not use the immediate output for reference, but refers to the previous image for averaging to facilitate recognition. In this way, we are able to reduce interference by the characteristics of the images. The experimental results show that after adopting this method, overall robustness and accuracy of facial expression recognition have been greatly improved compared to those obtained by only the convolution neural network (CNN).

Original languageEnglish
Title of host publicationProceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages120-123
Number of pages4
ISBN (Electronic)9781728105253
DOIs
Publication statusPublished - 2019 Jul
Event2019 International Conference on System Science and Engineering, ICSSE 2019 - Dong Hoi City, Quang Binh Province, Viet Nam
Duration: 2019 Jul 202019 Jul 21

Publication series

NameProceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019

Conference

Conference2019 International Conference on System Science and Engineering, ICSSE 2019
CountryViet Nam
CityDong Hoi City, Quang Binh Province
Period19/7/2019/7/21

Fingerprint

Facial Expression Recognition
Real-time
Convolution
High Speed
Cameras
Robustness
Neural networks
Facial Expression
Preprocessing
Averaging
Maintenance
Interference
Camera
Neural Networks
Moment
Output
Experimental Results

Keywords

  • average weighting method
  • convolution neural network (CNN)
  • facial expression recognition

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Safety, Risk, Reliability and Quality
  • Control and Optimization
  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems and Management

Cite this

Liu, K. C., Hsu, C. C., Wang, W. Y., & Chiang, H. H. (2019). Real-Time facial expression recognition based on cnn. In Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019 (pp. 120-123). [8823409] (Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSSE.2019.8823409

Real-Time facial expression recognition based on cnn. / Liu, Keng Cheng; Hsu, Chen Chien; Wang, Wei Yen; Chiang, Hsin Han.

Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 120-123 8823409 (Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019).

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

Liu, KC, Hsu, CC, Wang, WY & Chiang, HH 2019, Real-Time facial expression recognition based on cnn. in Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019., 8823409, Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019, Institute of Electrical and Electronics Engineers Inc., pp. 120-123, 2019 International Conference on System Science and Engineering, ICSSE 2019, Dong Hoi City, Quang Binh Province, Viet Nam, 19/7/20. https://doi.org/10.1109/ICSSE.2019.8823409
Liu KC, Hsu CC, Wang WY, Chiang HH. Real-Time facial expression recognition based on cnn. In Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 120-123. 8823409. (Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019). https://doi.org/10.1109/ICSSE.2019.8823409
Liu, Keng Cheng ; Hsu, Chen Chien ; Wang, Wei Yen ; Chiang, Hsin Han. / Real-Time facial expression recognition based on cnn. Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 120-123 (Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019).
@inproceedings{b7c549cf61f044aa9ab5161222b04027,
title = "Real-Time facial expression recognition based on cnn",
abstract = "In this paper, we propose a method for improving the robustness of real-Time facial expression recognition. Although there are many ways to improve the accuracy of facial expression recognition, a revamp of the training framework and image preprocessing allow better results in applications. One existing problem is that when the camera is capturing images in high speed, changes in image characteristics may occur at certain moments due to the influence of light and other factors. Such changes can result in incorrect recognition of the human facial expression. To solve this problem for smooth system operation and maintenance of recognition speed, we take changes in image characteristics at high speed capturing into account. The proposed method does not use the immediate output for reference, but refers to the previous image for averaging to facilitate recognition. In this way, we are able to reduce interference by the characteristics of the images. The experimental results show that after adopting this method, overall robustness and accuracy of facial expression recognition have been greatly improved compared to those obtained by only the convolution neural network (CNN).",
keywords = "average weighting method, convolution neural network (CNN), facial expression recognition",
author = "Liu, {Keng Cheng} and Hsu, {Chen Chien} and Wang, {Wei Yen} and Chiang, {Hsin Han}",
year = "2019",
month = "7",
doi = "10.1109/ICSSE.2019.8823409",
language = "English",
series = "Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "120--123",
booktitle = "Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019",

}

TY - GEN

T1 - Real-Time facial expression recognition based on cnn

AU - Liu, Keng Cheng

AU - Hsu, Chen Chien

AU - Wang, Wei Yen

AU - Chiang, Hsin Han

PY - 2019/7

Y1 - 2019/7

N2 - In this paper, we propose a method for improving the robustness of real-Time facial expression recognition. Although there are many ways to improve the accuracy of facial expression recognition, a revamp of the training framework and image preprocessing allow better results in applications. One existing problem is that when the camera is capturing images in high speed, changes in image characteristics may occur at certain moments due to the influence of light and other factors. Such changes can result in incorrect recognition of the human facial expression. To solve this problem for smooth system operation and maintenance of recognition speed, we take changes in image characteristics at high speed capturing into account. The proposed method does not use the immediate output for reference, but refers to the previous image for averaging to facilitate recognition. In this way, we are able to reduce interference by the characteristics of the images. The experimental results show that after adopting this method, overall robustness and accuracy of facial expression recognition have been greatly improved compared to those obtained by only the convolution neural network (CNN).

AB - In this paper, we propose a method for improving the robustness of real-Time facial expression recognition. Although there are many ways to improve the accuracy of facial expression recognition, a revamp of the training framework and image preprocessing allow better results in applications. One existing problem is that when the camera is capturing images in high speed, changes in image characteristics may occur at certain moments due to the influence of light and other factors. Such changes can result in incorrect recognition of the human facial expression. To solve this problem for smooth system operation and maintenance of recognition speed, we take changes in image characteristics at high speed capturing into account. The proposed method does not use the immediate output for reference, but refers to the previous image for averaging to facilitate recognition. In this way, we are able to reduce interference by the characteristics of the images. The experimental results show that after adopting this method, overall robustness and accuracy of facial expression recognition have been greatly improved compared to those obtained by only the convolution neural network (CNN).

KW - average weighting method

KW - convolution neural network (CNN)

KW - facial expression recognition

UR - http://www.scopus.com/inward/record.url?scp=85072919800&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072919800&partnerID=8YFLogxK

U2 - 10.1109/ICSSE.2019.8823409

DO - 10.1109/ICSSE.2019.8823409

M3 - Conference contribution

AN - SCOPUS:85072919800

T3 - Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019

SP - 120

EP - 123

BT - Proceedings of 2019 International Conference on System Science and Engineering, ICSSE 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -