Video-based detection of clinical depression in adolescents

Maddage, N, Low, L, Lech, M and Allen, N 2009, 'Video-based detection of clinical depression in adolescents', in Zhi-Pei Liang (ed.) Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Minneapolis, USA, 2 - 6 Sept 2009, pp. 3723-3726.


Document type: Conference Paper
Collection: Conference Papers

Title Video-based detection of clinical depression in adolescents
Author(s) Maddage, N
Low, L
Lech, M
Allen, N
Year 2009
Conference name 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'09)
Conference location Minneapolis, USA
Conference dates 2 - 6 Sept 2009
Proceedings title Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Editor(s) Zhi-Pei Liang
Publisher IEEE
Place of publication USA
Start page 3723
End page 3726
Total pages 4
Abstract We proposed a framework to detect the video contents of depressed and non-depressed subjects. First we characterized the expressed emotions in the video stream using Gabor wavelet features extracted at the facial landmarks which were detected using landmark model matching algorithm. Depressed and non-depressed class models were constructed using Gaussian Mixture models. Using 8 hours of video recordings, an hour of video recording per subject, and both gender and class balanced, we examined the effectiveness of both gender based and gender independent modeling approaches for depressed and non-depressed content classification. We found that the gender based content modeling approach improved the classification accuracy by 6% compared to the gender independent modeling approach, achieving 78.6% average accuracy.
Subjects Signal Processing
Keyword(s) Class models
Classification accuracy
Clinical depression
Content classification
Content modeling
Facial landmark
Gabor wavelets
Gaussian Mixture Model
Landmark model
Modeling approach
Video contents
Video streams
DOI - identifier 10.1109/IEMBS.2009.5334815
Copyright notice ©2009 IEEE
ISBN 9781424432967
Versions
Version Filter Type
Altmetric details:
Access Statistics: 245 Abstract Views  -  Detailed Statistics
Created: Fri, 09 Sep 2011, 07:50:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us