Facial expression recogntion in unconstrained environment

Andres Hernandez-Matamoros, Takayuki Nagai, Muhammad Attamimi, Mariko Nakano, Hector Perez-Meana

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

Abstract

© 2017 The authors and IOS Press. All rights reserved. The facial expression recognition has been a topic of active researches given a result the proposal of several efficient algorithms; however, in most cases they remain limited to controlled conditions situations. In this study, we tackle the challenge of recognizing emotions through the facial expression into activities inthe- wild adding the accuracy rate for each expression. To this end we an algorithm that allows accurate face expression recognition in an uncontrolled environment, that means different kind of illumination, backgrounds, occlusions, face's profiles, etc. Proposed system firstly detects different profile of face (left, frontal and right), Then it uses only the frames in which the face profile is frontal, in the next step the face regions of interest (ROI) are segmented automatically to carry out the feature extraction. We use a classifier based on clustering, it has the advantage that if a new class (emotion) is added, it is not necessary to train this completely. Proposed system was evaluated using short video clips of several pictures together with description sentences describing the main activity in the video. The evaluation results show that the proposed scheme is able to recognize the face's profiles with the recognition rate to approximately 93% and principal emotions in unconstrained video sequences.
Original languageAmerican English
Title of host publicationFacial expression recogntion in unconstrained environment
Pages525-538
Number of pages471
ISBN (Electronic)9781614997993
DOIs
StatePublished - 1 Jan 2017
EventFrontiers in Artificial Intelligence and Applications -
Duration: 1 Jan 2018 → …

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume297
ISSN (Print)0922-6389

Conference

ConferenceFrontiers in Artificial Intelligence and Applications
Period1/01/18 → …

Fingerprint

Feature extraction
Classifiers
Lighting
train
video
rate
evaluation

Cite this

Hernandez-Matamoros, A., Nagai, T., Attamimi, M., Nakano, M., & Perez-Meana, H. (2017). Facial expression recogntion in unconstrained environment. In Facial expression recogntion in unconstrained environment (pp. 525-538). (Frontiers in Artificial Intelligence and Applications; Vol. 297). https://doi.org/10.3233/978-1-61499-800-6-525
Hernandez-Matamoros, Andres ; Nagai, Takayuki ; Attamimi, Muhammad ; Nakano, Mariko ; Perez-Meana, Hector. / Facial expression recogntion in unconstrained environment. Facial expression recogntion in unconstrained environment. 2017. pp. 525-538 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{8b9218684275434d929825b3db544b4d,
title = "Facial expression recogntion in unconstrained environment",
abstract = "{\circledC} 2017 The authors and IOS Press. All rights reserved. The facial expression recognition has been a topic of active researches given a result the proposal of several efficient algorithms; however, in most cases they remain limited to controlled conditions situations. In this study, we tackle the challenge of recognizing emotions through the facial expression into activities inthe- wild adding the accuracy rate for each expression. To this end we an algorithm that allows accurate face expression recognition in an uncontrolled environment, that means different kind of illumination, backgrounds, occlusions, face's profiles, etc. Proposed system firstly detects different profile of face (left, frontal and right), Then it uses only the frames in which the face profile is frontal, in the next step the face regions of interest (ROI) are segmented automatically to carry out the feature extraction. We use a classifier based on clustering, it has the advantage that if a new class (emotion) is added, it is not necessary to train this completely. Proposed system was evaluated using short video clips of several pictures together with description sentences describing the main activity in the video. The evaluation results show that the proposed scheme is able to recognize the face's profiles with the recognition rate to approximately 93{\%} and principal emotions in unconstrained video sequences.",
author = "Andres Hernandez-Matamoros and Takayuki Nagai and Muhammad Attamimi and Mariko Nakano and Hector Perez-Meana",
year = "2017",
month = "1",
day = "1",
doi = "10.3233/978-1-61499-800-6-525",
language = "American English",
isbn = "9781614997993",
series = "Frontiers in Artificial Intelligence and Applications",
pages = "525--538",
booktitle = "Facial expression recogntion in unconstrained environment",

}

Hernandez-Matamoros, A, Nagai, T, Attamimi, M, Nakano, M & Perez-Meana, H 2017, Facial expression recogntion in unconstrained environment. in Facial expression recogntion in unconstrained environment. Frontiers in Artificial Intelligence and Applications, vol. 297, pp. 525-538, Frontiers in Artificial Intelligence and Applications, 1/01/18. https://doi.org/10.3233/978-1-61499-800-6-525

Facial expression recogntion in unconstrained environment. / Hernandez-Matamoros, Andres; Nagai, Takayuki; Attamimi, Muhammad; Nakano, Mariko; Perez-Meana, Hector.

Facial expression recogntion in unconstrained environment. 2017. p. 525-538 (Frontiers in Artificial Intelligence and Applications; Vol. 297).

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

TY - GEN

T1 - Facial expression recogntion in unconstrained environment

AU - Hernandez-Matamoros, Andres

AU - Nagai, Takayuki

AU - Attamimi, Muhammad

AU - Nakano, Mariko

AU - Perez-Meana, Hector

PY - 2017/1/1

Y1 - 2017/1/1

N2 - © 2017 The authors and IOS Press. All rights reserved. The facial expression recognition has been a topic of active researches given a result the proposal of several efficient algorithms; however, in most cases they remain limited to controlled conditions situations. In this study, we tackle the challenge of recognizing emotions through the facial expression into activities inthe- wild adding the accuracy rate for each expression. To this end we an algorithm that allows accurate face expression recognition in an uncontrolled environment, that means different kind of illumination, backgrounds, occlusions, face's profiles, etc. Proposed system firstly detects different profile of face (left, frontal and right), Then it uses only the frames in which the face profile is frontal, in the next step the face regions of interest (ROI) are segmented automatically to carry out the feature extraction. We use a classifier based on clustering, it has the advantage that if a new class (emotion) is added, it is not necessary to train this completely. Proposed system was evaluated using short video clips of several pictures together with description sentences describing the main activity in the video. The evaluation results show that the proposed scheme is able to recognize the face's profiles with the recognition rate to approximately 93% and principal emotions in unconstrained video sequences.

AB - © 2017 The authors and IOS Press. All rights reserved. The facial expression recognition has been a topic of active researches given a result the proposal of several efficient algorithms; however, in most cases they remain limited to controlled conditions situations. In this study, we tackle the challenge of recognizing emotions through the facial expression into activities inthe- wild adding the accuracy rate for each expression. To this end we an algorithm that allows accurate face expression recognition in an uncontrolled environment, that means different kind of illumination, backgrounds, occlusions, face's profiles, etc. Proposed system firstly detects different profile of face (left, frontal and right), Then it uses only the frames in which the face profile is frontal, in the next step the face regions of interest (ROI) are segmented automatically to carry out the feature extraction. We use a classifier based on clustering, it has the advantage that if a new class (emotion) is added, it is not necessary to train this completely. Proposed system was evaluated using short video clips of several pictures together with description sentences describing the main activity in the video. The evaluation results show that the proposed scheme is able to recognize the face's profiles with the recognition rate to approximately 93% and principal emotions in unconstrained video sequences.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85029232181&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85029232181&origin=inward

U2 - 10.3233/978-1-61499-800-6-525

DO - 10.3233/978-1-61499-800-6-525

M3 - Conference contribution

SN - 9781614997993

T3 - Frontiers in Artificial Intelligence and Applications

SP - 525

EP - 538

BT - Facial expression recogntion in unconstrained environment

ER -

Hernandez-Matamoros A, Nagai T, Attamimi M, Nakano M, Perez-Meana H. Facial expression recogntion in unconstrained environment. In Facial expression recogntion in unconstrained environment. 2017. p. 525-538. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-800-6-525