Back to Search
Start Over
A Statistical-Topological Feature Combination for Recognition of Isolated Hand Gestures from Kinect Based Depth Images
- Source :
- IWCIA, IWCIA, Jun 2017, Plovdiv, Bulgaria. ⟨10.1007/978-3-319-59108-7⟩, Lecture Notes in Computer Science ISBN: 9783319591070
- Publication Year :
- 2017
- Publisher :
- HAL CCSD, 2017.
-
Abstract
- International audience; Reliable hand gesture recognition is an important problem for automatic sign language recognition for the people with hearing and speech disabilities. In this paper, we create a new benchmark database of multi-oriented, isolated ASL numeric images using recently launched Kinect V2. Further, we design an effective statistical-topological feature combinations for recognition of the hand gestures using the available V1 sensor dataset and also over the new V2 dataset. For V1, our best accuracy is 98.4% which is comparable with the best one reported so far and for V2 we achieve an accuracy of 92.2% which is first of its kind.
- Subjects :
- Sign Language
Kinect
020204 information systems
Topological Features
0202 electrical engineering, electronic engineering, information engineering
[SCCO.COMP]Cognitive science/Computer science
020207 software engineering
Hand Gesture Recognition
Statistical
02 engineering and technology
Discrete Curve
Polygonal Simplification
Depth Data
Subjects
Details
- Language :
- English
- ISBN :
- 978-3-319-59107-0
- ISBNs :
- 9783319591070
- Database :
- OpenAIRE
- Journal :
- IWCIA, IWCIA, Jun 2017, Plovdiv, Bulgaria. ⟨10.1007/978-3-319-59108-7⟩, Lecture Notes in Computer Science ISBN: 9783319591070
- Accession number :
- edsair.doi.dedup.....ee6baf4c810cee02128f3a895d65965b