Micro-expression recognition by feature points tracking

Shuoqing Yao, Ning He, Huiquan Zhang, Osamu Yoshie

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

7 Citations (Scopus)

Abstract

One of the most interesting aspects of facial expression analysis is recognizing micro-expression. In this paper, a new feature tracking and alignment approach for micro-expression based on FACS systems and Tracking Learning Detection(TLD) is presented. The basic point for detecting first frame feature point is based on Hough Forest, and in order to increase the accuracy, we extracted features by Local Binary Pattern(LBP) as initialization. Unlike many previous works, the proposed approach applies conceptual area in perspective of human cognition. And this approach aims to track the extracted features and quantifies changing trend of these points for analyzing micro-expression. To estimate our approach's rationality, we conducted experiments on the CASME and SMIC facial expression database. The results show that the proposed approach is effective and performs well in recognizing some specific micro-expressions. Furthermore, the proposed approach is more accurate than previous methods based on Temporal Interpolation Model(TIM).

Original languageEnglish
Title of host publicationIEEE International Conference on Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479923854
DOIs
Publication statusPublished - 2014
Event2014 10th International Conference on Communications, COMM 2014 - Bucharest
Duration: 2014 May 292014 May 31

Other

Other2014 10th International Conference on Communications, COMM 2014
CityBucharest
Period14/5/2914/5/31

Fingerprint

Interpolation
Experiments

Keywords

  • Hough Forest
  • Local Binary Pattern
  • Micro-Expression
  • Temporal Interpolation Model
  • Tracking Learning Detection

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications

Cite this

Yao, S., He, N., Zhang, H., & Yoshie, O. (2014). Micro-expression recognition by feature points tracking. In IEEE International Conference on Communications [6866671] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICComm.2014.6866671

Micro-expression recognition by feature points tracking. / Yao, Shuoqing; He, Ning; Zhang, Huiquan; Yoshie, Osamu.

IEEE International Conference on Communications. Institute of Electrical and Electronics Engineers Inc., 2014. 6866671.

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

Yao, S, He, N, Zhang, H & Yoshie, O 2014, Micro-expression recognition by feature points tracking. in IEEE International Conference on Communications., 6866671, Institute of Electrical and Electronics Engineers Inc., 2014 10th International Conference on Communications, COMM 2014, Bucharest, 14/5/29. https://doi.org/10.1109/ICComm.2014.6866671
Yao S, He N, Zhang H, Yoshie O. Micro-expression recognition by feature points tracking. In IEEE International Conference on Communications. Institute of Electrical and Electronics Engineers Inc. 2014. 6866671 https://doi.org/10.1109/ICComm.2014.6866671
Yao, Shuoqing ; He, Ning ; Zhang, Huiquan ; Yoshie, Osamu. / Micro-expression recognition by feature points tracking. IEEE International Conference on Communications. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{66e888cb15f9433193f2f6ae7e380a86,
title = "Micro-expression recognition by feature points tracking",
abstract = "One of the most interesting aspects of facial expression analysis is recognizing micro-expression. In this paper, a new feature tracking and alignment approach for micro-expression based on FACS systems and Tracking Learning Detection(TLD) is presented. The basic point for detecting first frame feature point is based on Hough Forest, and in order to increase the accuracy, we extracted features by Local Binary Pattern(LBP) as initialization. Unlike many previous works, the proposed approach applies conceptual area in perspective of human cognition. And this approach aims to track the extracted features and quantifies changing trend of these points for analyzing micro-expression. To estimate our approach's rationality, we conducted experiments on the CASME and SMIC facial expression database. The results show that the proposed approach is effective and performs well in recognizing some specific micro-expressions. Furthermore, the proposed approach is more accurate than previous methods based on Temporal Interpolation Model(TIM).",
keywords = "Hough Forest, Local Binary Pattern, Micro-Expression, Temporal Interpolation Model, Tracking Learning Detection",
author = "Shuoqing Yao and Ning He and Huiquan Zhang and Osamu Yoshie",
year = "2014",
doi = "10.1109/ICComm.2014.6866671",
language = "English",
isbn = "9781479923854",
booktitle = "IEEE International Conference on Communications",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Micro-expression recognition by feature points tracking

AU - Yao, Shuoqing

AU - He, Ning

AU - Zhang, Huiquan

AU - Yoshie, Osamu

PY - 2014

Y1 - 2014

N2 - One of the most interesting aspects of facial expression analysis is recognizing micro-expression. In this paper, a new feature tracking and alignment approach for micro-expression based on FACS systems and Tracking Learning Detection(TLD) is presented. The basic point for detecting first frame feature point is based on Hough Forest, and in order to increase the accuracy, we extracted features by Local Binary Pattern(LBP) as initialization. Unlike many previous works, the proposed approach applies conceptual area in perspective of human cognition. And this approach aims to track the extracted features and quantifies changing trend of these points for analyzing micro-expression. To estimate our approach's rationality, we conducted experiments on the CASME and SMIC facial expression database. The results show that the proposed approach is effective and performs well in recognizing some specific micro-expressions. Furthermore, the proposed approach is more accurate than previous methods based on Temporal Interpolation Model(TIM).

AB - One of the most interesting aspects of facial expression analysis is recognizing micro-expression. In this paper, a new feature tracking and alignment approach for micro-expression based on FACS systems and Tracking Learning Detection(TLD) is presented. The basic point for detecting first frame feature point is based on Hough Forest, and in order to increase the accuracy, we extracted features by Local Binary Pattern(LBP) as initialization. Unlike many previous works, the proposed approach applies conceptual area in perspective of human cognition. And this approach aims to track the extracted features and quantifies changing trend of these points for analyzing micro-expression. To estimate our approach's rationality, we conducted experiments on the CASME and SMIC facial expression database. The results show that the proposed approach is effective and performs well in recognizing some specific micro-expressions. Furthermore, the proposed approach is more accurate than previous methods based on Temporal Interpolation Model(TIM).

KW - Hough Forest

KW - Local Binary Pattern

KW - Micro-Expression

KW - Temporal Interpolation Model

KW - Tracking Learning Detection

UR - http://www.scopus.com/inward/record.url?scp=84907300004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907300004&partnerID=8YFLogxK

U2 - 10.1109/ICComm.2014.6866671

DO - 10.1109/ICComm.2014.6866671

M3 - Conference contribution

AN - SCOPUS:84907300004

SN - 9781479923854

BT - IEEE International Conference on Communications

PB - Institute of Electrical and Electronics Engineers Inc.

ER -