Hand Posture Recognition Using Skeletal Data and Distance Descriptor
Open Access
- 20 March 2020
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 10 (6) , 2132
Abstract
In this paper, a method for the recognition of static hand postures based on skeletal data was presented. A novel descriptor was proposed. It encodes information about distances between particular hand points. Five different classifiers were tested, including four common methods and a proposed modification of nearest neighbor classifier, which can distinguish between posture classes differing mostly in hand orientation. The experiments were performed using three challenging datasets of gestures from Polish and American Sign Languages. The proposed method was compared with other approaches found in the literature. It outperforms every compared method, including our previous work, in terms of recognition rate.Keywords
Funding Information
- Minister of Science and Higher Education of the Republic of Poland (Regional Initiative of Excellence 027/RID/2018/19)
This publication has 42 references indexed in Scilit:
- American Sign Language Recognition Using Leap Motion Sensor2014
- Hand gesture recognition with leap motion and kinect devices2014
- An Analysis of the Precision and Reliability of the Leap Motion Sensor and Its Suitability for Static and Dynamic TrackingSensors, 2014
- The Leap Motion controller2013
- Analysis of the Accuracy and Robustness of the Leap Motion ControllerSensors, 2013
- Vision based hand gesture recognition for human computer interaction: a surveyArtificial Intelligence Review, 2012
- Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images2002
- Bagging predictorsMachine Learning, 1996
- Support-vector networksMachine Learning, 1995
- Discriminant Analysis and Statistical Pattern RecognitionTechnometrics, 1993