Can body expressions contribute to automatic depression analysis?

Abstract

Abstract-Depression is one of the most common mental health disorders with strong adverse effects on personal and social functioning. The absence of any objective diagnostic aid for depression leads to a range of subjective biases in initial diagnosis and ongoing monitoring. Psychologists use various visual cues in their assessment to quantify depression such as facial expressions, eye contact and head movements. This paper studies the contribution of (upper) body expressions and gestures for automatic depression analysis. A framework based on space-time interest points and bag of words is proposed for the analysis of upper body and facial movements. Salient interest points are selected using clustering. The major contribution of this paper lies in the creation of a bag of body expressions and a bag of facial dynamics for assessing the contribution of different body parts for depression analysis. Head movement analysis is performed by selecting rigid facial fiducial points and a new histogram of head movements is proposed. The experiments are performed on real-world clinical data where video clips of patients and healthy controls are recorded during interactive interview sessions. The results show the effectiveness of the proposed system to evaluate the contribution of various body parts in depression analysis.

Relative Body Parts Movement for Automatic Depression Analysis

“…Furthermore, the data corpus in [18] contained video recordings of the (partial) upper body and face, which limited the analysis to the upper body only. One of the findings of our previous work [2] was that the head movement and upper body movement provide discriminative information for analysing depression.…”

“…Inspired from our previous findings in automatic depression analysis [18], [2], [1] and recent work in the field of human action recognition [19], [21], we propose a system, which fuses the holistic body motion based bag-of-words approach with the parts detector based body parts motion patterns to overcome the limitations of [19], [21].…”

“…Earlier approaches [6], [10], [18], [2] have looked at either face dynamics or body parts such as head movement. However, the relationships between the parts are not explored in them.…”

“…It is possible to build systems, which can predict neurological problems such as depression, pain and stress etc. Recently, affective computing techniques have been applied to depression detection [1], [2]. This paper focusses on depression detection based on the relative motion in body parts and holistic body movements.…”

Learning a sparse codebook of facial and body microexpressions for emotion recognition

“…The idea of combining facial expressions and body gestures for emotion recognition has recently been explored in the literature [38,2,16]. Shan et al [38] extract the local space-time features from two separate video feeds, one containing only facial expressions and another containing upper body movements, recorded simultaneously; the two streams of features are then fused using CCA [12].…”