Towards Identification of Hypomimia in Parkinson's Disease
Based on Face Recognition Methods

D 2018

Towards Identification of Hypomimia in Parkinson's Disease Based on Face Recognition Methods

RAJNOHA, M.; J. MEKYSKA; R. BURGET; Ilona ELIÁŠOVÁ; Milena KOŠŤÁLOVÁ et al.

Základní údaje

Originální název

Towards Identification of Hypomimia in Parkinson's Disease Based on Face Recognition Methods

Autoři

RAJNOHA, M.; J. MEKYSKA; R. BURGET; Ilona ELIÁŠOVÁ; Milena KOŠŤÁLOVÁ a Irena REKTOROVÁ

Vydání

NEW YORK, 2018 10TH INTERNATIONAL CONGRESS ON ULTRA MODERN TELECOMMUNICATIONS AND CONTROL SYSTEMS AND WORKSHOPS (ICUMT 2018): EMERGING TECHNOLOGIES FOR CONNECTED SOCIETY, od s. 1-4, 4 s. 2018

Nakladatel

IEEE

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

20205 Automation and control systems

Stát vydavatele

Rusko

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

URL

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14110/18:00113819

Organizační jednotka

Lékařská fakulta

ISBN

978-1-5386-9360-5

ISSN

UT WoS

000459238500052

EID Scopus

2-s2.0-85062780000

Klíčová slova anglicky

Parkinson's disease; hypomimia; face recognition; machine learning

Změněno: 11. 5. 2020 13:38, Mgr. Tereza Miškechová

Anotace

V originále

Hypomimia manifested as an expressionless face with little or no sense of animation is a typical symptom of Parkinson's disease (PD). Although some researchers tried to quantify and diagnose the hypomimia based on the analysis of video-recordings, a study dealing with a possibility of its identification using the simple static face analysis is missing. The goal of this work is therefore to verify whether PD hypomimia can be detected even from static face images. For this purpose we enrolled 50 PD patients and 50 age-and gender-matched healthy controls. Parameterization based on face recognition methods in combination with conventional classifiers (random forests, XG-Boost, etc.) were used to automatically identify PD hypomimia. Among the classifiers, the decision tree algorithm achieved the best accuracy (67.33 %). The results suggest that automatic static face analysis can support PD hypomimia diagnosis, nevertheless is not accurate enough to outperform the approaches based on video-recordings processing.

Citovat

RAJNOHA, M.; J. MEKYSKA; R. BURGET; Ilona ELIÁŠOVÁ; Milena KOŠŤÁLOVÁ a Irena REKTOROVÁ. Towards Identification of Hypomimia in Parkinson's Disease Based on Face Recognition Methods. Online. In 2018 10TH INTERNATIONAL CONGRESS ON ULTRA MODERN TELECOMMUNICATIONS AND CONTROL SYSTEMS AND WORKSHOPS (ICUMT 2018): EMERGING TECHNOLOGIES FOR CONNECTED SOCIETY. NEW YORK: IEEE, 2018, s. 1-4. ISBN 978-1-5386-9360-5.

@inproceedings{1650139,
   author = {Rajnoha, M. and Mekyska, J. and Burget, R. and Eliášová, Ilona and Košťálová, Milena and Rektorová, Irena},
   address = {NEW YORK},
   booktitle = {2018 10TH INTERNATIONAL CONGRESS ON ULTRA MODERN TELECOMMUNICATIONS AND CONTROL SYSTEMS AND WORKSHOPS (ICUMT 2018): EMERGING TECHNOLOGIES FOR CONNECTED SOCIETY},
   keywords = {Parkinson's disease; hypomimia; face recognition; machine learning},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {NEW YORK},
   isbn = {978-1-5386-9360-5},
   pages = {1-4},
   publisher = {IEEE},
   title = {Towards Identification of Hypomimia in Parkinson's Disease Based on Face Recognition Methods},
   url = {https://ieeexplore.ieee.org/document/8631249},
   year = {2018}
}

TY  - CONF
ID  - 1650139
AU  - Rajnoha, M. - Mekyska, J. - Burget, R. - Eliášová, Ilona - Košťálová, Milena - Rektorová, Irena
PY  - 2018
TI  - Towards Identification of Hypomimia in Parkinson's Disease Based on Face Recognition Methods
PB  - IEEE
CY  - NEW YORK
SN  - 9781538693605
KW  - Parkinson's disease
KW  - hypomimia
KW  - face recognition
KW  - machine learning
UR  - https://ieeexplore.ieee.org/document/8631249
L2  - https://ieeexplore.ieee.org/document/8631249
N2  - Hypomimia manifested as an expressionless face with little or no sense of animation is a typical symptom of Parkinson's disease (PD). Although some researchers tried to quantify and diagnose the hypomimia based on the analysis of video-recordings, a study dealing with a possibility of its identification using the simple static face analysis is missing. The goal of this work is therefore to verify whether PD hypomimia can be detected even from static face images. For this purpose we enrolled 50 PD patients and 50 age-and gender-matched healthy controls. Parameterization based on face recognition methods in combination with conventional classifiers (random forests, XG-Boost, etc.) were used to automatically identify PD hypomimia. Among the classifiers, the decision tree algorithm achieved the best accuracy (67.33 %). The results suggest that automatic static face analysis can support PD hypomimia diagnosis, nevertheless is not accurate enough to outperform the approaches based on video-recordings processing.
ER  -

RAJNOHA, M.; J. MEKYSKA; R. BURGET; Ilona ELIÁŠOVÁ; Milena KOŠŤÁLOVÁ a Irena REKTOROVÁ. Towards Identification of Hypomimia in Parkinson's Disease Based on Face Recognition Methods. Online. In \textit{2018 10TH INTERNATIONAL CONGRESS ON ULTRA MODERN TELECOMMUNICATIONS AND CONTROL SYSTEMS AND WORKSHOPS (ICUMT 2018): EMERGING TECHNOLOGIES FOR CONNECTED SOCIETY}. NEW YORK: IEEE, 2018, s.~1-4. ISBN~978-1-5386-9360-5.

Přehled o publikaci