Combining temporal interpolation and DCNN for faster recognition of micro-expressions in video sequences

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

9 Citations (Scopus)

Abstract

Micro-expressions are the hidden human emotions that are short lived and are very hard to detect them in real time conversations. Micro-expressions recognition has proven to be an important behavior source for lie detection during crime interrogation. SMIC and CASME II are the two widely used, spontaneous micro-expressions datasets which are available publicly with baseline results that uses LBP-TOP for feature extraction. Estimation of correct parameters is the key factor for feature extraction using LBP-TOP, which results in long computation time. In this paper, the video sequences are interpolated using temporal interpolation(TIM) and then the facial features are extracted using deep convolutional neural network(DCNN) on CUDA enabled General Purpose Graphics Processing Unit(GPGPU) system. Results show that the proposed combination of DCNN and TIM can achieve better performance than the results published in baseline publications. The feature extraction time is reduced due to the usage of GPU enabled systems.

Original languageEnglish
Title of host publication2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages699-703
Number of pages5
ISBN (Electronic)9781509020287
DOIs
Publication statusPublished - 02-11-2016
Event5th International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016 - Jaipur, India
Duration: 21-09-201624-09-2016

Conference

Conference5th International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016
CountryIndia
CityJaipur
Period21-09-1624-09-16

Fingerprint

Feature extraction
Interpolation
Neural networks
Crime
Graphics processing unit

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Science (miscellaneous)
  • Computer Networks and Communications
  • Hardware and Architecture

Cite this

Mayya, V., Pai, R. M., & Pai, M. M. M. (2016). Combining temporal interpolation and DCNN for faster recognition of micro-expressions in video sequences. In 2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016 (pp. 699-703). [7732128] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICACCI.2016.7732128
Mayya, Veena ; Pai, Radhika M. ; Pai, M. M.Manohara. / Combining temporal interpolation and DCNN for faster recognition of micro-expressions in video sequences. 2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 699-703
@inproceedings{cec5f82f90d04dcfbca430b07e19f7b5,
title = "Combining temporal interpolation and DCNN for faster recognition of micro-expressions in video sequences",
abstract = "Micro-expressions are the hidden human emotions that are short lived and are very hard to detect them in real time conversations. Micro-expressions recognition has proven to be an important behavior source for lie detection during crime interrogation. SMIC and CASME II are the two widely used, spontaneous micro-expressions datasets which are available publicly with baseline results that uses LBP-TOP for feature extraction. Estimation of correct parameters is the key factor for feature extraction using LBP-TOP, which results in long computation time. In this paper, the video sequences are interpolated using temporal interpolation(TIM) and then the facial features are extracted using deep convolutional neural network(DCNN) on CUDA enabled General Purpose Graphics Processing Unit(GPGPU) system. Results show that the proposed combination of DCNN and TIM can achieve better performance than the results published in baseline publications. The feature extraction time is reduced due to the usage of GPU enabled systems.",
author = "Veena Mayya and Pai, {Radhika M.} and Pai, {M. M.Manohara}",
year = "2016",
month = "11",
day = "2",
doi = "10.1109/ICACCI.2016.7732128",
language = "English",
pages = "699--703",
booktitle = "2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Mayya, V, Pai, RM & Pai, MMM 2016, Combining temporal interpolation and DCNN for faster recognition of micro-expressions in video sequences. in 2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016., 7732128, Institute of Electrical and Electronics Engineers Inc., pp. 699-703, 5th International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016, Jaipur, India, 21-09-16. https://doi.org/10.1109/ICACCI.2016.7732128

Combining temporal interpolation and DCNN for faster recognition of micro-expressions in video sequences. / Mayya, Veena; Pai, Radhika M.; Pai, M. M.Manohara.

2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 699-703 7732128.

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

TY - GEN

T1 - Combining temporal interpolation and DCNN for faster recognition of micro-expressions in video sequences

AU - Mayya, Veena

AU - Pai, Radhika M.

AU - Pai, M. M.Manohara

PY - 2016/11/2

Y1 - 2016/11/2

N2 - Micro-expressions are the hidden human emotions that are short lived and are very hard to detect them in real time conversations. Micro-expressions recognition has proven to be an important behavior source for lie detection during crime interrogation. SMIC and CASME II are the two widely used, spontaneous micro-expressions datasets which are available publicly with baseline results that uses LBP-TOP for feature extraction. Estimation of correct parameters is the key factor for feature extraction using LBP-TOP, which results in long computation time. In this paper, the video sequences are interpolated using temporal interpolation(TIM) and then the facial features are extracted using deep convolutional neural network(DCNN) on CUDA enabled General Purpose Graphics Processing Unit(GPGPU) system. Results show that the proposed combination of DCNN and TIM can achieve better performance than the results published in baseline publications. The feature extraction time is reduced due to the usage of GPU enabled systems.

AB - Micro-expressions are the hidden human emotions that are short lived and are very hard to detect them in real time conversations. Micro-expressions recognition has proven to be an important behavior source for lie detection during crime interrogation. SMIC and CASME II are the two widely used, spontaneous micro-expressions datasets which are available publicly with baseline results that uses LBP-TOP for feature extraction. Estimation of correct parameters is the key factor for feature extraction using LBP-TOP, which results in long computation time. In this paper, the video sequences are interpolated using temporal interpolation(TIM) and then the facial features are extracted using deep convolutional neural network(DCNN) on CUDA enabled General Purpose Graphics Processing Unit(GPGPU) system. Results show that the proposed combination of DCNN and TIM can achieve better performance than the results published in baseline publications. The feature extraction time is reduced due to the usage of GPU enabled systems.

UR - http://www.scopus.com/inward/record.url?scp=85007359830&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007359830&partnerID=8YFLogxK

U2 - 10.1109/ICACCI.2016.7732128

DO - 10.1109/ICACCI.2016.7732128

M3 - Conference contribution

SP - 699

EP - 703

BT - 2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Mayya V, Pai RM, Pai MMM. Combining temporal interpolation and DCNN for faster recognition of micro-expressions in video sequences. In 2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 699-703. 7732128 https://doi.org/10.1109/ICACCI.2016.7732128