Automated recognition system of statistic gestures via kinect sensor

Saule Kudubayeva, Dmitry Ryumin, Marat Kalghanov, Almatova Assem

2016

Closed access Metadata (CSL-JSON)
DOI 10.1109/icaict.2016.7991709
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The paper presents a system of recognition of elements of a sign language. The description of the elements of Kazakh sign language database is given. The algorithm of allocation of human hands on images obtained via the Kinect sensor and the method of calculation of informative video features of hands gestures are suggested. The implementation of recognition of isolate hand gestures on the basis of the elements of decision theory is given. The results of the automated system operation are illustrated.