An Implementation of Real-Time Numeral Recognizer Based on Hand Gesture Using Both Gradient and Positional Information


KIPS Transactions on Software and Data Engineering, Vol. 2, No. 3, pp. 199-204, Mar. 2013
10.3745/KTSDE.2013.2.3.199,   PDF Download:

Abstract

An implementation method of real-time numeral recognizer based on gesture is presented in this paper for various information devices. The proposed algorithm steadily captures the motion of a hand on 3D open space with the Kinect sensor. The captured hand motion is simplified with PCA, in order to preserve the trace consistency and to minimize the trace variations due to noises and size changes. In addition, we also propose a new HMM using both the gradient and the positional features of the simplified hand stroke. As the result, the proposed algorithm has robust characteristics to the variations of the size and speed of hand motion. The recognition rate is increased up to 30%, because of this combined model. Experimental results showed that the proposed algorithm gives a high recognition rate about 98%.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
J. H. Kim, Y. W. Park, K. P. Han, "An Implementation of Real-Time Numeral Recognizer Based on Hand Gesture Using Both Gradient and Positional Information," KIPS Transactions on Software and Data Engineering, vol. 2, no. 3, pp. 199-204, 2013. DOI: 10.3745/KTSDE.2013.2.3.199.

[ACM Style]
Ji Ho Kim, Yang Woo Park, and Kyu Phil Han. 2013. An Implementation of Real-Time Numeral Recognizer Based on Hand Gesture Using Both Gradient and Positional Information. KIPS Transactions on Software and Data Engineering, 2, 3, (2013), 199-204. DOI: 10.3745/KTSDE.2013.2.3.199.