Hand Gesture Classification Using Inaudible Frequency 


Vol. 43,  No. 10, pp. 1664-1669, Oct.  2018
10.7840/kics.2018.43.10.1664


PDF
  Abstract

As the 4th Industrial Revolution progresses, recognizing and distinguishing human actions and behaviors are becoming an important issue. In this paper, we propose a method to classify the hand gestures by generating the sound of inaudible frequency band that can not be heard by the human ear with the smartphone and recording the reflected signal. In the proposed method, the recorded sound data is imaged using a Short-Time Fourier Transform and applied to the Convolution Neural Network (CNN) model to classify the hand gestures. Experimental results show that the proposed method gives 94% accuracy for 5 hand gestures.

  Statistics
Cumulative Counts from November, 2022
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. Kim and S. Choi, "Hand Gesture Classification Using Inaudible Frequency," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 10, pp. 1664-1669, 2018. DOI: 10.7840/kics.2018.43.10.1664.

[ACM Style]

Jinhyuck Kim and Sunwoong Choi. 2018. Hand Gesture Classification Using Inaudible Frequency. The Journal of Korean Institute of Communications and Information Sciences, 43, 10, (2018), 1664-1669. DOI: 10.7840/kics.2018.43.10.1664.

[KICS Style]

Jinhyuck Kim and Sunwoong Choi, "Hand Gesture Classification Using Inaudible Frequency," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 10, pp. 1664-1669, 10. 2018. (https://doi.org/10.7840/kics.2018.43.10.1664)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880