Neural-Net Classification for Spatio-Temporal Descriptor Based Depression Analysis

Jyoti Dhall, Abhinav Dhall, Roland Goecke, Michael Breakspear, Gordon Parker

Research output: A Conference proceeding or a Chapter in BookConference contribution

24 Citations (Scopus)
1 Downloads (Pure)

Abstract

Depression is a severe psychiatric disorder. Despite the high prevalence, current clinical practice depends almost exclusively on self-report and clinical opinion, risking a range of subjective biases. This paper focuses on depression analysis based on visual cues from facial expressions and upper body movements. The proposed diagnostic support system is based on computing spatio-temporal features from video sequences. Space Time Interest Points are computed for the videos for analysing the upper body movements and a temporal visual words dictionary is learned from them. Intra-facial muscle movement is captured by computing a LBP-TOP based codebook. Various neural-net classifiers are explored and compared with a SVM. The approach is evaluated on real-world clinical data from interactive interviews with depressed and healthy subjects.
Original languageEnglish
Title of host publication21st International Conference on Pattern Recognition (ICPR 2012)
EditorsRichard Bowden
Place of PublicationTsukuba, Japan
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages2634-2638
Number of pages5
ISBN (Electronic)9784990644109
ISBN (Print)9781467322164
Publication statusPublished - 15 Nov 2012
Event21st International Conference on Pattern Recognition (ICPR 2012) - Tsukuba, Tsukuba, Japan
Duration: 11 Nov 201215 Nov 2012

Conference

Conference21st International Conference on Pattern Recognition (ICPR 2012)
Abbreviated titleICPR 2012
CountryJapan
CityTsukuba
Period11/11/1215/11/12

Fingerprint

Glossaries
Muscle
Classifiers
Neural networks
Psychiatry

Cite this

Dhall, J., Dhall, A., Goecke, R., Breakspear, M., & Parker, G. (2012). Neural-Net Classification for Spatio-Temporal Descriptor Based Depression Analysis. In R. Bowden (Ed.), 21st International Conference on Pattern Recognition (ICPR 2012) (pp. 2634-2638). Tsukuba, Japan: IEEE, Institute of Electrical and Electronics Engineers.
Dhall, Jyoti ; Dhall, Abhinav ; Goecke, Roland ; Breakspear, Michael ; Parker, Gordon. / Neural-Net Classification for Spatio-Temporal Descriptor Based Depression Analysis. 21st International Conference on Pattern Recognition (ICPR 2012). editor / Richard Bowden. Tsukuba, Japan : IEEE, Institute of Electrical and Electronics Engineers, 2012. pp. 2634-2638
@inproceedings{e5e64297ebd749a49db29c6ca55f37e1,
title = "Neural-Net Classification for Spatio-Temporal Descriptor Based Depression Analysis",
abstract = "Depression is a severe psychiatric disorder. Despite the high prevalence, current clinical practice depends almost exclusively on self-report and clinical opinion, risking a range of subjective biases. This paper focuses on depression analysis based on visual cues from facial expressions and upper body movements. The proposed diagnostic support system is based on computing spatio-temporal features from video sequences. Space Time Interest Points are computed for the videos for analysing the upper body movements and a temporal visual words dictionary is learned from them. Intra-facial muscle movement is captured by computing a LBP-TOP based codebook. Various neural-net classifiers are explored and compared with a SVM. The approach is evaluated on real-world clinical data from interactive interviews with depressed and healthy subjects.",
keywords = "Depression analysis, Neural Network, Spatio-temporal analysis",
author = "Jyoti Dhall and Abhinav Dhall and Roland Goecke and Michael Breakspear and Gordon Parker",
year = "2012",
month = "11",
day = "15",
language = "English",
isbn = "9781467322164",
pages = "2634--2638",
editor = "Richard Bowden",
booktitle = "21st International Conference on Pattern Recognition (ICPR 2012)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Dhall, J, Dhall, A, Goecke, R, Breakspear, M & Parker, G 2012, Neural-Net Classification for Spatio-Temporal Descriptor Based Depression Analysis. in R Bowden (ed.), 21st International Conference on Pattern Recognition (ICPR 2012). IEEE, Institute of Electrical and Electronics Engineers, Tsukuba, Japan, pp. 2634-2638, 21st International Conference on Pattern Recognition (ICPR 2012), Tsukuba, Japan, 11/11/12.

Neural-Net Classification for Spatio-Temporal Descriptor Based Depression Analysis. / Dhall, Jyoti; Dhall, Abhinav; Goecke, Roland; Breakspear, Michael; Parker, Gordon.

21st International Conference on Pattern Recognition (ICPR 2012). ed. / Richard Bowden. Tsukuba, Japan : IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 2634-2638.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Neural-Net Classification for Spatio-Temporal Descriptor Based Depression Analysis

AU - Dhall, Jyoti

AU - Dhall, Abhinav

AU - Goecke, Roland

AU - Breakspear, Michael

AU - Parker, Gordon

PY - 2012/11/15

Y1 - 2012/11/15

N2 - Depression is a severe psychiatric disorder. Despite the high prevalence, current clinical practice depends almost exclusively on self-report and clinical opinion, risking a range of subjective biases. This paper focuses on depression analysis based on visual cues from facial expressions and upper body movements. The proposed diagnostic support system is based on computing spatio-temporal features from video sequences. Space Time Interest Points are computed for the videos for analysing the upper body movements and a temporal visual words dictionary is learned from them. Intra-facial muscle movement is captured by computing a LBP-TOP based codebook. Various neural-net classifiers are explored and compared with a SVM. The approach is evaluated on real-world clinical data from interactive interviews with depressed and healthy subjects.

AB - Depression is a severe psychiatric disorder. Despite the high prevalence, current clinical practice depends almost exclusively on self-report and clinical opinion, risking a range of subjective biases. This paper focuses on depression analysis based on visual cues from facial expressions and upper body movements. The proposed diagnostic support system is based on computing spatio-temporal features from video sequences. Space Time Interest Points are computed for the videos for analysing the upper body movements and a temporal visual words dictionary is learned from them. Intra-facial muscle movement is captured by computing a LBP-TOP based codebook. Various neural-net classifiers are explored and compared with a SVM. The approach is evaluated on real-world clinical data from interactive interviews with depressed and healthy subjects.

KW - Depression analysis

KW - Neural Network

KW - Spatio-temporal analysis

M3 - Conference contribution

SN - 9781467322164

SP - 2634

EP - 2638

BT - 21st International Conference on Pattern Recognition (ICPR 2012)

A2 - Bowden, Richard

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Tsukuba, Japan

ER -

Dhall J, Dhall A, Goecke R, Breakspear M, Parker G. Neural-Net Classification for Spatio-Temporal Descriptor Based Depression Analysis. In Bowden R, editor, 21st International Conference on Pattern Recognition (ICPR 2012). Tsukuba, Japan: IEEE, Institute of Electrical and Electronics Engineers. 2012. p. 2634-2638