Abstract

In this paper, we investigate the issues associated with facial expression recognition of Traumatic Brain Insured (TBI) patients in a realistic scenario. These patients have restricted or limited muscle movements with reduced facial expressions along with non-cooperative behavior, impaired reasoning and inappropriate responses. All these factors make automatic understanding of their expressions more complex. While the existing facial expression recognition systems showed high accuracy by taking data from healthy subjects, their performance is yet to be proved for real TBI patient data by considering the aforementioned challenges. To deal with this, we devised scenarios for data collection from the real TBI patients, collected data which is very challenging to process, devised effective way of data preprocessing so that good quality faces can be extracted from the patients facial video for expression analysis, and finally, employed a state-of-the-art deep learning framework to exploit spatio-temporal information of facial video frames in expression analysis. The experimental results confirms the difficulty in processing real TBI patients data, while showing that better face quality ensures better performance in this case.
Original languageEnglish
Title of host publicationVISAPP 2018 : 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.
EditorsAlain Tremeau, Jose Braz, Francisco Imai
Number of pages9
Volume4
PublisherSCITEPRESS Digital Library
Publication date2018
Pages522-530
ISBN (Print)978-989-758-290-5
ISBN (Electronic)978-989-758-290-5
DOIs
Publication statusPublished - 2018
EventInternational Conference on Computer Vision Theory and Applications - Funchal, Madeira, Portugal, Madeira, Portugal
Duration: 27 Jan 201829 Jan 2018
http://visapp.visigrapp.org/Home.aspx

Conference

ConferenceInternational Conference on Computer Vision Theory and Applications
LocationFunchal, Madeira, Portugal
CountryPortugal
CityMadeira
Period27/01/201829/01/2018
Internet address

Fingerprint

Brain
Muscle
Processing

Keywords

  • Computer Vision
  • Face Detection
  • Facial Landmarks
  • Facial Expressions
  • Convolution Neural Networks
  • Long-Short Term Memory
  • Traumatic Brain Injured Patients

Cite this

Ilyas, C. M. A., Haque, M. A., Rehm, M., Nasrollahi, K., & Moeslund, T. B. (2018). Facial Expression Recognition for Traumatic Brain Injured Patients. In A. Tremeau, J. Braz, & F. Imai (Eds.), VISAPP 2018: 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. (Vol. 4, pp. 522-530). SCITEPRESS Digital Library. https://doi.org/10.5220/0006721305220530
Ilyas, Chaudhary Muhammad Aqdus ; Haque, Mohammad Ahsanul ; Rehm, Matthias ; Nasrollahi, Kamal ; Moeslund, Thomas B. / Facial Expression Recognition for Traumatic Brain Injured Patients. VISAPP 2018: 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.. editor / Alain Tremeau ; Jose Braz ; Francisco Imai. Vol. 4 SCITEPRESS Digital Library, 2018. pp. 522-530
@inproceedings{e886fd3bf91a44bead75b1a4df82a58c,
title = "Facial Expression Recognition for Traumatic Brain Injured Patients",
abstract = "In this paper, we investigate the issues associated with facial expression recognition of Traumatic Brain Insured (TBI) patients in a realistic scenario. These patients have restricted or limited muscle movements with reduced facial expressions along with non-cooperative behavior, impaired reasoning and inappropriate responses. All these factors make automatic understanding of their expressions more complex. While the existing facial expression recognition systems showed high accuracy by taking data from healthy subjects, their performance is yet to be proved for real TBI patient data by considering the aforementioned challenges. To deal with this, we devised scenarios for data collection from the real TBI patients, collected data which is very challenging to process, devised effective way of data preprocessing so that good quality faces can be extracted from the patients facial video for expression analysis, and finally, employed a state-of-the-art deep learning framework to exploit spatio-temporal information of facial video frames in expression analysis. The experimental results confirms the difficulty in processing real TBI patients data, while showing that better face quality ensures better performance in this case.",
keywords = "Computer Vision, Face Detection, Facial Landmarks, Facial Expressions, Convolution Neural Networks, Long-Short Term Memory, Traumatic Brain Injured Patients",
author = "Ilyas, {Chaudhary Muhammad Aqdus} and Haque, {Mohammad Ahsanul} and Matthias Rehm and Kamal Nasrollahi and Moeslund, {Thomas B.}",
year = "2018",
doi = "10.5220/0006721305220530",
language = "English",
isbn = "978-989-758-290-5",
volume = "4",
pages = "522--530",
editor = "Alain Tremeau and Jose Braz and Francisco Imai",
booktitle = "VISAPP 2018",
publisher = "SCITEPRESS Digital Library",

}

Ilyas, CMA, Haque, MA, Rehm, M, Nasrollahi, K & Moeslund, TB 2018, Facial Expression Recognition for Traumatic Brain Injured Patients. in A Tremeau, J Braz & F Imai (eds), VISAPP 2018: 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.. vol. 4, SCITEPRESS Digital Library, pp. 522-530, International Conference on Computer Vision Theory and Applications, Madeira, Portugal, 27/01/2018. https://doi.org/10.5220/0006721305220530

Facial Expression Recognition for Traumatic Brain Injured Patients. / Ilyas, Chaudhary Muhammad Aqdus; Haque, Mohammad Ahsanul; Rehm, Matthias; Nasrollahi, Kamal; Moeslund, Thomas B.

VISAPP 2018: 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.. ed. / Alain Tremeau; Jose Braz; Francisco Imai. Vol. 4 SCITEPRESS Digital Library, 2018. p. 522-530.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Facial Expression Recognition for Traumatic Brain Injured Patients

AU - Ilyas, Chaudhary Muhammad Aqdus

AU - Haque, Mohammad Ahsanul

AU - Rehm, Matthias

AU - Nasrollahi, Kamal

AU - Moeslund, Thomas B.

PY - 2018

Y1 - 2018

N2 - In this paper, we investigate the issues associated with facial expression recognition of Traumatic Brain Insured (TBI) patients in a realistic scenario. These patients have restricted or limited muscle movements with reduced facial expressions along with non-cooperative behavior, impaired reasoning and inappropriate responses. All these factors make automatic understanding of their expressions more complex. While the existing facial expression recognition systems showed high accuracy by taking data from healthy subjects, their performance is yet to be proved for real TBI patient data by considering the aforementioned challenges. To deal with this, we devised scenarios for data collection from the real TBI patients, collected data which is very challenging to process, devised effective way of data preprocessing so that good quality faces can be extracted from the patients facial video for expression analysis, and finally, employed a state-of-the-art deep learning framework to exploit spatio-temporal information of facial video frames in expression analysis. The experimental results confirms the difficulty in processing real TBI patients data, while showing that better face quality ensures better performance in this case.

AB - In this paper, we investigate the issues associated with facial expression recognition of Traumatic Brain Insured (TBI) patients in a realistic scenario. These patients have restricted or limited muscle movements with reduced facial expressions along with non-cooperative behavior, impaired reasoning and inappropriate responses. All these factors make automatic understanding of their expressions more complex. While the existing facial expression recognition systems showed high accuracy by taking data from healthy subjects, their performance is yet to be proved for real TBI patient data by considering the aforementioned challenges. To deal with this, we devised scenarios for data collection from the real TBI patients, collected data which is very challenging to process, devised effective way of data preprocessing so that good quality faces can be extracted from the patients facial video for expression analysis, and finally, employed a state-of-the-art deep learning framework to exploit spatio-temporal information of facial video frames in expression analysis. The experimental results confirms the difficulty in processing real TBI patients data, while showing that better face quality ensures better performance in this case.

KW - Computer Vision

KW - Face Detection

KW - Facial Landmarks

KW - Facial Expressions

KW - Convolution Neural Networks

KW - Long-Short Term Memory

KW - Traumatic Brain Injured Patients

UR - http://www.scopus.com/inward/record.url?scp=85047860286&partnerID=8YFLogxK

U2 - 10.5220/0006721305220530

DO - 10.5220/0006721305220530

M3 - Article in proceeding

SN - 978-989-758-290-5

VL - 4

SP - 522

EP - 530

BT - VISAPP 2018

A2 - Tremeau, Alain

A2 - Braz, Jose

A2 - Imai, Francisco

PB - SCITEPRESS Digital Library

ER -

Ilyas CMA, Haque MA, Rehm M, Nasrollahi K, Moeslund TB. Facial Expression Recognition for Traumatic Brain Injured Patients. In Tremeau A, Braz J, Imai F, editors, VISAPP 2018: 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.. Vol. 4. SCITEPRESS Digital Library. 2018. p. 522-530 https://doi.org/10.5220/0006721305220530