A model-based hand gesture recognition system
Machine Vision and Applications
Modeling Multimodal Expression of User's Affective Subjective Experience
User Modeling and User-Adapted Interaction
Digital Image Processing (3rd Edition)
Digital Image Processing (3rd Edition)
Recovery of upper body poses in static images based on joints detection
Pattern Recognition Letters
Automatic temporal segment detection and affect recognition from face and body display
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on human computing
Adjacency Matrix Based Objects Representation for Human Identification in Images
ARTCOM '09 Proceedings of the 2009 International Conference on Advances in Recent Technologies in Communication and Computing
| Hi-index | 0.00 |
This paper introduces an upper body pose recognition and classifier system. Our objective is to analyze, design and implement the above mentioned system to enhance the machine's understanding of humans based upon affective behavior of humans. This work follows vision based techniques for recognition and identification of a vast range of non-overlapping body poses. The problem in body-posture identification is the inherent complexity of poses, like same pose can be present in a number of different scenarios or situations. Therefore it is inappropriate to guess the exact pose without identifying facial gestures, hand gestures and speech. Hence our approach is to identify the exact position of arms, head, shoulders and torso, so that, we can estimate the intensity of any pose and also identify possible emotion(s) under which this pose is expressed. The accuracy of this system is as good as 92%.