Depression and suicide tendency recognition method fusing body language, micro-expression and language

Abstract

The invention provides a depression and suicide tendency recognition method fusing body language, micro-expression and language. The method comprises the following steps: collecting videos and audiosby using Kinect with an infrared camera, and respectively converting video information and audio information into feature text description; carrying out information fusion on the generated feature text description, and carrying out sentiment classification on a processing result by utilizing self-organizing mapping (SOM) and a compensation layer; and marking the obtained person possibly having thedepression emotion or suicide tendency, and observing them. Static body movement and dynamic body movement are considered, and higher efficiency is achieved. The Kinect is used for data acquisition,and the invention is non-invasive, high in performance and easy to operate.

Description

technical field [0001] The invention belongs to the field of emotion recognition, in particular to a depression and suicide tendency recognition method integrating body language, micro-expression and language. Background technique [0002] The accelerated pace of life and changes in the social environment have made many people feel a lot of pressure, resulting in depression, and even self-mutilation or suicide. It is useful to monitor people's emotions in order to detect emotional problems early on and prevent depression or suicidal ideation. Human emotions can be recognized in various ways, such as electrocardiogram (ECG), electroencephalogram (EEG) (K. Takahashi, "Remarks on emotion recognition from multi-modal bio-potential signals", Proc.IEEE Int.Conf.Ind .Technol.(ICIT),vol.3,pp.1138-1143,Jun.2004.), speech, facial expressions, etc. Among various emotional signals, physiological signals are widely used in emotion recognition. Human movement has also become a new feat...

AI Technical Summary

Problems solved by technology

Technically, audio and video (F.Xu, J.Zhang and J.Z.Wang, “Microexpression Identification and Categorization Using a FacialDynamics Map,” IEEE Transactions on Effective Computing, vol.8, issue 2, pp.1- 1, 2017.) are readily available but susceptible to noise

In principle, single detection of static posture or single detection of dynamic motion (H.Wallbott, "Bodily Expressions of Emotion," European J.SocialPsychology, vol.28, pp.879-896, 1998.M.Coulson, "Attributing Emotion to Static Body Postures: Recognition Accuracy, Confusions, and Viewpoint Dependence," J.Nonverbal Behavior, vol.28, no.2, pp.117-139, 2004. J. Burgoon, L. Guerrero, and K. Floyd, Nonverbal Communication. Allyn and Bacon, 2010.) to recognize emotion has lower computational complexity, but also leads to lower recognition accuracy

Images