Automatic Facial Expression Recognition Using DCNN

Research output: Contribution to journalArticle

32 Citations (Scopus)

Abstract

Face depicts a wide range of information about identity, age, sex, race as well as emotional and mental state. Facial expressions play crucial role in social interactions and commonly used in the behavioral interpretation of emotions. Automatic facial expression recognition is one of the interesting and challenging problem in computer vision due to its potential applications such as Human Computer Interaction(HCI), behavioral science, video games etc. In this paper, a novel method for automatically recognizing facial expressions using Deep Convolutional Neural Network(DCNN) features is proposed. The proposed model focuses on recognizing the facial expressions of an individual from a single image. The feature extraction time is significantly reduced due to the usage of general purpose graphic processing unit (GPGPU). From an evaluation on two publicly available facial expression datasets, we have found that using DCNN features, we can achieve the state-of-the-art recognition rate.

Original languageEnglish
Pages (from-to)453-461
Number of pages9
JournalProcedia Computer Science
Volume93
DOIs
Publication statusPublished - 2016

Fingerprint

Neural networks
Human computer interaction
Computer vision
Feature extraction
Graphics processing unit

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

@article{e52bb118ddd54c549540a3572379388d,
title = "Automatic Facial Expression Recognition Using DCNN",
abstract = "Face depicts a wide range of information about identity, age, sex, race as well as emotional and mental state. Facial expressions play crucial role in social interactions and commonly used in the behavioral interpretation of emotions. Automatic facial expression recognition is one of the interesting and challenging problem in computer vision due to its potential applications such as Human Computer Interaction(HCI), behavioral science, video games etc. In this paper, a novel method for automatically recognizing facial expressions using Deep Convolutional Neural Network(DCNN) features is proposed. The proposed model focuses on recognizing the facial expressions of an individual from a single image. The feature extraction time is significantly reduced due to the usage of general purpose graphic processing unit (GPGPU). From an evaluation on two publicly available facial expression datasets, we have found that using DCNN features, we can achieve the state-of-the-art recognition rate.",
author = "Veena Mayya and Pai, {Radhika M.} and {Manohara Pai}, {M. M.}",
year = "2016",
doi = "10.1016/j.procs.2016.07.233",
language = "English",
volume = "93",
pages = "453--461",
journal = "Procedia Computer Science",
issn = "1877-0509",
publisher = "Elsevier BV",

}

Automatic Facial Expression Recognition Using DCNN. / Mayya, Veena; Pai, Radhika M.; Manohara Pai, M. M.

In: Procedia Computer Science, Vol. 93, 2016, p. 453-461.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic Facial Expression Recognition Using DCNN

AU - Mayya, Veena

AU - Pai, Radhika M.

AU - Manohara Pai, M. M.

PY - 2016

Y1 - 2016

N2 - Face depicts a wide range of information about identity, age, sex, race as well as emotional and mental state. Facial expressions play crucial role in social interactions and commonly used in the behavioral interpretation of emotions. Automatic facial expression recognition is one of the interesting and challenging problem in computer vision due to its potential applications such as Human Computer Interaction(HCI), behavioral science, video games etc. In this paper, a novel method for automatically recognizing facial expressions using Deep Convolutional Neural Network(DCNN) features is proposed. The proposed model focuses on recognizing the facial expressions of an individual from a single image. The feature extraction time is significantly reduced due to the usage of general purpose graphic processing unit (GPGPU). From an evaluation on two publicly available facial expression datasets, we have found that using DCNN features, we can achieve the state-of-the-art recognition rate.

AB - Face depicts a wide range of information about identity, age, sex, race as well as emotional and mental state. Facial expressions play crucial role in social interactions and commonly used in the behavioral interpretation of emotions. Automatic facial expression recognition is one of the interesting and challenging problem in computer vision due to its potential applications such as Human Computer Interaction(HCI), behavioral science, video games etc. In this paper, a novel method for automatically recognizing facial expressions using Deep Convolutional Neural Network(DCNN) features is proposed. The proposed model focuses on recognizing the facial expressions of an individual from a single image. The feature extraction time is significantly reduced due to the usage of general purpose graphic processing unit (GPGPU). From an evaluation on two publicly available facial expression datasets, we have found that using DCNN features, we can achieve the state-of-the-art recognition rate.

UR - http://www.scopus.com/inward/record.url?scp=84985930513&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84985930513&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2016.07.233

DO - 10.1016/j.procs.2016.07.233

M3 - Article

AN - SCOPUS:84985930513

VL - 93

SP - 453

EP - 461

JO - Procedia Computer Science

JF - Procedia Computer Science

SN - 1877-0509

ER -