Title :
Fingertip tracking and multi-point gesture recognition
Author :
Wensheng, Li ; Huaiwen, He
Author_Institution :
Zhongshan Inst., Univ. of Electron. Sci. & Technol. of China, Zhongshan, China
Abstract :
This paper presents a method of multi-point gesture recognition based on machine vision, which can achieve similar features of multi-touch like iPhone with a camera. Firstly we present a CamShift based method to track fingertips, then we present a method of multi-point gesture recognition based on BP neural network. The method was realized and tested through DirectShow, and results show that the proposed methods are reliable and efficient for the tracking of fingertips and for the recognition of multi-point gestures.
Keywords :
backpropagation; computer vision; gesture recognition; neural nets; BP neural network; fingertip tracking; iPhone; machine vision; multipoint gesture recognition; Artificial neural networks; Fingers; Gesture recognition; Image color analysis; Mice; Signal processing algorithms; Target tracking; BP Neural Network; CamShift algorithm; Machine Vision; Multi-Point Gesture Recognition; Tracking of Fingertip;
Conference_Titel :
Intelligent Signal Processing and Communication Systems (ISPACS), 2010 International Symposium on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-7369-4
DOI :
10.1109/ISPACS.2010.5704778
