Gesture Segmentation Using Spiking Neural Networks Inspired by the Visual System

DOI

10.2991/aiie-15.2015.52How to use a DOI?

Keywords

gesture segmentation; spiking neural network; visual system; motion detection; skin detection

Abstract

The human visual system demonstrates powerful image processing functionalities. Inspired by the behaviour of the human visual system, a method of gesture segmentation with the complex background is investigated based on fusion of outputs from two kinds of spiking neural networks. The structures and the properties of the two networks are detailed in this paper. One of two networks performs the movement region of gesture. Meanwhile, another spiking neural network performs identification of skin area according to the biologically colour processing mechanism. Finally, two outputs from two neural networks are integrated to segment the meaningful region of gestures from the video image sequence. Simulation results show that the proposed algorithm works efficiently and can perform gesture segmentation with the satisfying accuracy for dynamic visual image sequence under complex background. It is promising to apply this approach to video processing domain and robotic visual systems.

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  - L.P. Huang
AU  - Q.X. Wu
AU  - G.R. Zhang
AU  - X. Wang
PY  - 2015/07
DA  - 2015/07
TI  - Gesture Segmentation Using Spiking Neural Networks Inspired by the Visual System
BT  - Proceedings of the 2015 International Conference on Artificial Intelligence and Industrial Engineering
PB  - Atlantis Press
SP  - 184
EP  - 187
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-15.2015.52
DO  - 10.2991/aiie-15.2015.52
ID  - Huang2015/07
ER  -