Analysis of depression based on facial cues on a captured motion picture

College

College of Computer Studies

Department/Unit

Software Technology

Document Type

Conference Proceeding

Source Title

IEEE 3rd International Conference on Signal and Image Processing, ICSIP 2018

First Page

49

Last Page

54

Publication Date

2018

Abstract

Depression is one of the causes of suicide in the world next to other health issues that makes up an alarming point of mortality living in this lifetime. Melancholy that in the field of computer vision and signal processing has been tackled in various ways. Thus, this paper presents the classification model of detecting depression based on local binary pattern (LBP) texture features an image processing approach for pattern recognition on images. The study used the video recording from the SEMAINE database. The face image is cropped from a video and extracting Uniformed LBP features in every single frame. Part of the classification is to implement PCA eigenvalues from the original features to see the effects. The result of the accuracy was 81% of the SVM using RBF kernel classifier when detecting Depressed to Not Depressed Behavior on a captured motion picture.

html

Digitial Object Identifier (DOI)

10.1109/SIPROCESS.2018.8600523

Disciplines

Computer Sciences

Keywords

Computer vision; Facial expression; Depression, Mental

Upload File

wf_no

This document is currently not available here.

Share

COinS