single-jc.php

JACIII Vol.21 No.2 pp. 247-250
doi: 10.20965/jaciii.2017.p0247
(2017)

Short Paper:

An Improved Otsu’s Thresholding Algorithm on Gesture Segmentation

Chongshan Lv, Ting Zhang, and Chengyuan Liu

School of Automation, Beijing Institute of Technology
Beijing 100081, China

Received:
July 8, 2016
Accepted:
November 5, 2016
Online released:
March 15, 2017
Published:
March 20, 2017
Keywords:
gesture segmentation, gaussian model, skin segmentation, Otsu algorithm
Abstract

In gesture recognition systems, segmenting gestures from complex background is the hardest and the most critical part. Gesture segmentation is the prerequisite of following image processing, and the result of segmentation has a direct influence on the result of gesture recognition. This paper proposed an algorithm of adaptive threshold gesture segmentation based on skin color. First of all, the image should be transformed from RGB color space to YCbCr color space. After eliminating luminance component Y, similarity graph of skin color will be obtained from the Gaussian model. Then Otsu adaptive threshold algorithm is used to carry out binary processing for the similarity graph of skin color. After the segmentation of skin color regions, the morphology method is used to process binary image for determining the location of hands. Experimental results show that the detailed segmentation of skin color using the dynamic-adaptive threshold can improve noise resistance and can produce better results.

References
  1. [1] J. Sheng, “The Application of Hand Gesture Recognition in Human Computer Interaction,” Computer Knowledge and Technology, Vol.35, No.2, pp. 72-74, 2011.
  2. [2] X. Cao, J. Zhao, and M. Li, “Monocular Vision Gesture Segmentation Based on Skin Color and Motion Detection,” J. of Hunan University (Natural Sciences), Vol.12, No.3, pp. 17-19, 2011.
  3. [3] J. Yang and W. Lu, “Skin-color modeling and adaptation,” Springer Berlin Heidelberg, pp. 687-694, 1997.
  4. [4] L. Sun and L. Zhang, “Technologies of hand gesture recognition based on vision,” Computer Technology and Development, Vol.18, No.10, pp. 214-216, 2008.
  5. [5] P. Wang, Z. Cai, and W. Liu, “EM estimation of PDF parameters for Gaussian mixture processes,” SHENGXUE JISHU, Vol.26, No.3, pp. 498, 2007.
  6. [6] Z. Liu and J. Liu, “Research on Face Detection Algorithm Based on Complexional Segmentation,” Computer Engineering, Vol.4, No.1, pp. 61-63, 2007.
  7. [7] W. Sun, W. Zhang, X. Zhang, G. Chen, and C. Lv, “Adaptive Face Location for Detecting Fatigue Driving,” Modern Transportation Technology, Issue 1, pp. 73-76, 2009.
  8. [8] X. Zeng, W. Zuo, and Y. Shi, “A novel self-adaptive threshold chosen method of complexion similarity image,” Computer Applications and Software, Vol.27, No.9, pp. 125-127, 2010.
  9. [9] M. Zhao and Y. Zhao, “Skin color segmentation based on improved 2D Otsu,” 2010 Int. Conf. on IEEE Electrical and Control Engineering (ICECE), pp. 1954-1957, 2010.
  10. [10] S. L. Phung, A. Bouzerdoum, and D. Chai, “Skin segmentation using color pixel classification: analysis and comparison,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.27, No.1, pp. 148-154, 2005.
  11. [11] X. Cheng, “An Edge Detection Operator Based on Mathematic Morphology,” J. of Hebei Polytechnic University, 2009.
  12. [12] C. Xu and G. H. Peng, “Fast algorithm for Otsu thresholding algorithm,” J. of Computer Applications, pp. 1258-1260, 2014.
  13. [13] B. Wang and T. Liu, “Simulation research on gesture segmentation algorithm,” J. of Computer Simulation, 2015.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, IE9,10,11, Opera.

Last updated on May. 26, 2017