Edge Based Grid Super-Imposition for Crowd Emotion Recognition
This addresses the challenge of emotion recognition in chaotic, multi-person environments, which is incremental as it extends existing methods from individual to group settings.
The study tackled the problem of detecting spontaneous emotions in group and crowd settings by using edge detection with grid superimposition to extract features, achieving an overall accuracy of 70.9% for the group emotion classifier.
Numerous automatic continuous emotion detection system studies have examined mostly use of videos and images containing individual person expressing emotions. This study examines the detection of spontaneous emotions in a group and crowd settings. Edge detection was used with a grid of lines superimposition to extract the features. The feature movement in terms of movement from the reference point was used to track across sequences of images from the color channel. Additionally the video data capturing was done on spontaneous emotions invoked by watching sports events from group of participants. The method was view and occlusion independent and the results were not affected by presence of multiple people chaotically expressing various emotions. The edge thresholds of 0.2 and grid thresholds of 20 showed the best accuracy results. The overall accuracy of the group emotion classifier was 70.9%.