Facial Analysis Method for Pain Detection

Oana Subea; George Suciu

Future Access Enablers for Ubiquitous and Intelligent Infrastructures. 4th EAI International Conference, FABULOUS 2019, Sofia, Bulgaria, March 28-29, 2019, Proceedings

Research Article

Facial Analysis Method for Pain Detection

Download

265 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-030-23976-3_17,
    author={Oana Subea and George Suciu},
    title={Facial Analysis Method for Pain Detection},
    proceedings={Future Access Enablers for Ubiquitous and Intelligent Infrastructures. 4th EAI International Conference, FABULOUS 2019, Sofia, Bulgaria, March 28-29, 2019, Proceedings},
    proceedings_a={FABULOUS},
    year={2019},
    month={9},
    keywords={Image processing Facial recognition HOG(Histogram of oriented Gradients) Random Forest DLIB},
    doi={10.1007/978-3-030-23976-3_17}
}

Oana Subea
George Suciu
Year: 2019
Facial Analysis Method for Pain Detection
FABULOUS
Springer
DOI: 10.1007/978-3-030-23976-3_17

Oana Subea^,*, George Suciu¹^,*

1: R&D Department BEIA Consult International

*Contact email: oana.subea@beia.ro, george@beia.ro

Abstract

Facial expression recognition has been an active research topic for many years. In this paper a method for automatically recognizing pain intensity in images with facial expressions will be implemented. The method presented will contain a first step in which the face and the important points on the face will be located using the DLIB library. The second step consists of the calculation of HOG-type traits in order to describe the face found. The traits will be used to train a Random Forest (RF) regressor that will estimate the intensity of the pain. Training and testing will be done on the public UNBC-McMaster shoulder Pain Expression Archive database, using Python programming.

Keywords: Image processing Facial recognition HOG(Histogram of oriented Gradients) Random Forest DLIB

Published: 2019-09-17
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-030-23976-3_17