Title :
A Novel Vision based Finger-writing Character Recognition System
Author :
Jin, Lianwen ; Yang, Duanduan ; Zhen, Li-Xin ; Huang, Jian-Cheng
Author_Institution :
Sch. of Electron. & Inf. Eng., South China Univ. of Technol., Guangzhou
Abstract :
A new vision based finger writing character recognition system (FWCRS) is proposed in this paper. The FWCRS allows people to write characters virtually just using his finger-tip (we call this "finger-writing"). The trajectories of the finger-tip are tracked and reconstructed as a kind of inkless character pattern and finally recognized by a classifier. In this paper, a simple but effective background model is built for the FWCRS to segment human finger from cluttered background. A robust fingertip detection algorithm based on feature matching is presented. The finger-writing character is finally recognized by a DTW classifier. Experiments show that the FWCRS can recognize finger-writing uppercase & lowercase English characters with the accuracy of 95.6%, 98.5% respectively
Keywords :
computer vision; feature extraction; handwriting recognition; handwritten character recognition; image segmentation; DTW classifier; dynamic time warping; feature matching; fingertip trajectory tracking; human finger segmentation; inkless character pattern; robust fingertip detection; virtual character writing; vision finger-writing character recognition system; Character recognition; Computer vision; Digital cameras; Equations; Fingers; Human computer interaction; Pattern recognition; Robustness; Trajectory; Writing;
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2521-0
DOI :
10.1109/ICPR.2006.145
