Vision-Based Two-Arm Gesture Recognition by Using Longest Common Subsequence 


Vol. 33,  No. 5, pp. 371-377, May  2008


PDF
  Abstract

In this paper, we present a framework for vision-based two-arm gesture recognition. To capture the motion information of the hands, we perform color-based tracking algorithm using adaptive kernel for each frame. And a feature selection algorithm is performed to classify the motion information into four different phrases. By using gesture phrase information, we build a gesture model which consists of a probability of the symbols and a symbol sequence which is learned from the longest common subsequence. Finally, we present a similarity measurement for two-arm gesture recognition by using the proposed gesture models. In the experimental results, we show the efficiency of the proposed feature selection method, and the simplicity and the robustness of the recognition algorithm.

  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]

C. Choi, J. Ahn, H. Byun, "Vision-Based Two-Arm Gesture Recognition by Using Longest Common Subsequence," The Journal of Korean Institute of Communications and Information Sciences, vol. 33, no. 5, pp. 371-377, 2008. DOI: .

[ACM Style]

Cheolmin Choi, Jung-Ho Ahn, and Hyeran Byun. 2008. Vision-Based Two-Arm Gesture Recognition by Using Longest Common Subsequence. The Journal of Korean Institute of Communications and Information Sciences, 33, 5, (2008), 371-377. DOI: .

[KICS Style]

Cheolmin Choi, Jung-Ho Ahn, Hyeran Byun, "Vision-Based Two-Arm Gesture Recognition by Using Longest Common Subsequence," The Journal of Korean Institute of Communications and Information Sciences, vol. 33, no. 5, pp. 371-377, 5. 2008.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880