Algorithm Design of Gesture Word Recognition Based on Vision
Yanling Zhang, Zhengqiang Yang, Yunfeng Wang
Available Online April 2015.
- https://doi.org/10.2991/icmra-15.2015.61How to use a DOI?
- gesture word recognition; threshold; gesture segmentation; centroid location; extreme algorithm
- 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.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
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 - 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 - https://doi.org/10.2991/icmra-15.2015.61 ID - Zhang2015/04 ER -