Algorithm Design of Gesture Word Recognition Based on Vision

DOI

10.2991/icmra-15.2015.61How to use a DOI?

Keywords

gesture word recognition; threshold; gesture segmentation; centroid location; extreme algorithm

Abstract

Through the analysis and process of visual images of gesture words, this paper realizes the recognition of the gesture words, and this will lay a good foundation to recognize gesture language. Firstly the acquired images are preprocessed by denoising; secondly the gesture images are segmented from the background images by setting their thresholds, and the outline of the gesture images information is obtained under morphology operations; thirdly by extracting centroid coordinates of the target gestures, the gesture images are positioned and segmented; in the end, the gesture words can be identified by calculating the extreme values to the modules. The above algorithm is validated through the Matlab software. The experimental results show that the algorithm is reliable and has good robustness.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yanling Zhang
AU  - Zhengqiang Yang
AU  - Yunfeng Wang
PY  - 2015/04
DA  - 2015/04
TI  - Algorithm Design of Gesture Word Recognition Based on Vision
BT  - Proceedings of the 3rd International Conference on Mechatronics, Robotics and Automation
PB  - Atlantis Press
SP  - 307
EP  - 310
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmra-15.2015.61
DO  - 10.2991/icmra-15.2015.61
ID  - Zhang2015/04
ER  -