Gesture recognition is an emerging cross-discipline research field, which aims at interpreting human gestures and associating them to a well-defined meaning.
It has been used as a mean for supporting human to machine interaction in several applications of robotics, artificial intelligence, and machine learning. In this paper, we propose a system able to recognize human body gestures which implements a constrained training set reduction technique.
This allows the system for a real-time execution. The system has been tested on a publicly available dataset of 7,000 gestures, and experimental results have highlighted that at the cost of a little decrease in the maximum achievable recognition accuracy, the required time for recognition can be dramatically reduced.
This article is authored also by Synbrain data scientists and collaborators. READ THE FULL ARTICLE