Video-based detection of the clinical depression in adolescents

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.

Dynamic Multimodal Measurement of Depression Severity Using Deep Autoencoding

“…The latter use signal processing, computer vision, and pattern recognition methodologies. From the computer-science perspective, research has sought to identify depression from vocal utterances [8], [9], [10], [11], [12], [13], facial expression [14], [15], [16], [17], head movements/pose [18], [16], [19], body movements [18], and gaze [20]. While most research is limited to a single modality, there is increasing interest in multimodal approaches to depression detection [21], [22].…”

Cross-cultural detection of depression from nonverbal behaviour

“…Recognising depression from video data has also been investigated, including facial activities and expressions (e.g. [15], [19], [20], [21]), general movements and posture of the body [22], [23], head pose and movement [20], [23], [24], and gaze and eye activity [22], [25]. Moreover, most previous studies on the automatic detection of depression have only investigated a single modality.…”

Automatic Assessment of Depression Based on Visual Cues: A Systematic Review

“…Potential benefits from multimodal approaches have also been discussed in [64]. Finally, gender-based classification has been supported by many of the reported approaches to perform better [86], [116], [138], [146], [150].…”

“…In one of the earliest studies, the corpus constructed by the Oregon Research Institute (ORI), was used to test the approach of Maddage et al [138] for video-based depression detection in adolescents. The corpus comprised recordings from eight adolescents (four in each class).…”