DOI QR코드

DOI QR Code

Gesture Recognition Using Zernike Moments Masked By Duel Ring

이중 링 마스크 저니키 모멘트를 이용한 손동작 인식

  • Park, Jung-Su (Graduate School of Advanced Image Science, Multimedia, and Film, Chung-Ang University) ;
  • Kim, Tae-Yong (Graduate School of Advanced Image Science, Multimedia, and Film, Chung-Ang University)
  • 박정수 (중앙대학교 첨단영상대학원) ;
  • 김태용 (중앙대학교 첨단영상대학원)
  • Received : 2013.06.25
  • Published : 2013.10.25

Abstract

Generally, when we apply zernike moments value for matching, we can use those moments value obtained from projecting image information under circumscribed circle to zernike basis function. However, the problem is that the power of discrimination can be reduced because hand images include lots of overlapped information due to its special characteristic. On the other hand, when distinguishing hand poses, information in specific area of image information except for overlapped information can increase the power of discrimination. In this paper, in order to solve problems like those, we design R3 ring mask by combining image obtained from R2 ring mask, which can weight information of the power of discrimination and image obtained from R1 ring mask, which eliminate the overlapped information. The moments which are obtained by R3 ring mask decrease operational time by reducing dimension through principle component analysis. In order to confirm the superiority of the suggested method, we conducted some experiments by comparing our method to other method using seven different hand poses.

일반적으로 저니키 모멘트 값을 이용한 매칭 시에는 외접원 안에 속하는 이미지 정보를 Zernike 기저함수로 투영시켜 얻은 모멘트 값을 이용하여 매칭에 사용한다. 하지만 손 이미지의 특성상 무게중심 부근에 중복되는 정보가 많이 포함되는데 이로 인해 변별력이 떨어질 수 있는 문제점이 있다. 또한 중복되는 정보를 제외한 이미지 정보들 중에서 특정 영역에 있는 정보들은 손의 모양정보를 구분하는데 변별력을 높여줄 수 있다. 본 논문에서는 이러한 문제점을 해결하기 위해 중복되는 정보를 제거하는 R1 링 마스크를 통해 얻은 이미지와 변별력을 높여 줄 수 있는 정보에 가중치를 부여하는 R2 링 마스크를 통해 얻은 이미지를 결합하여 R3 링 마스크를 설계한다. R3 링 마스크를 이용하여 얻은 모멘트들을 주성분분석(PCA)을 통해 차원을 축소함으로써 매칭량을 감소시킨다. 제안한 방법의 우수성을 확인하기 위해 7가지 손 모양을 다른 방법과 비교실험 하였으며, 그 결과 우수성을 확인 할 수 있었다.

Keywords

References

  1. R. Watson, "A survey of Gesture Recognirion Techniques," Technical Report, TCD-CS- 1993-11, pp. 1-31, 1993.
  2. K. W. Kim, W. J. Lee, C. H. Jeon, "Dynamic Hand Gesture Recognition using Guide Lines," The Institute of Electronics Engineers of Korea, vol. 47, no. 5, pp. 469-477, Sep 2010.
  3. J. H. Yun, C. H. Lee, "Design of Computer Vision Interface by Recognizing Hand Motion," The Institute of Electronics Engineers of Korea, vol. 47, no. 3, pp. 256-265, May 2010.
  4. N. R. Shin, B. G. Heo, K. C. Hong, "Development of Hand Gesture Recognition Technic based on Image's Skin Color Information," Korea Computer Congress, vol. 37, no. 1, pp. 484-489, 2010.
  5. S. I. Lee, H. S. Min, H. C. Shin, E. G. Lim, D. H. Hwang, Y. M. No, "Hand posture recognition robust to rotation using temporal correlation between adjacent frames," Journal of Korea Multimedia Society, vol. 13, no. 11, pp. 1630-1642, Nov 2010.
  6. http://en.wikipedia.org/wiki/Kinect
  7. A. Khotanzad, Y. H. Hong, "Invariant image recognition by zernike moments," IEEE Transactions on Pattern analysis and Machine Intelligence, vol. 12, no. 5, pp. 489-497, May 1990. https://doi.org/10.1109/34.55109
  8. C. H. The, R T. Chin, "On Image Analysis by the methods of moments," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, no.4, pp. 496-513, Jul 1988. https://doi.org/10.1109/34.3913
  9. M. Kirby, L. Sirovich, "Application of the Karhunen-Loeve procedure for the characterization of human faces," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 103-108, Jan 1990. https://doi.org/10.1109/34.41390
  10. D. Swets, "Using discriminant eigenfeatures for image retrieval," IEEE Transaction on Pattern Analysis and Machine Intelligence vol. 18, no. 8, pp. 831-836, Aug 1996. https://doi.org/10.1109/34.531802
  11. H. I. Suk, J. H. Lee, S. W. Lee, "Real-Time Hand Pose Tracking and Finger Action Recognition Based on 3D Hand Modeling," Journal of KIISE, vol. 35, no. 12, pp. 780-788, Dec 2008.
  12. J. D. Kim, H. G. Kim, "Zernike Moments Shape Descriptor with Region Partitioning," The Korean Society of Broadcast Engineers, pp. 53-57, Nov 1999.
  13. C. W. Chong, P. Raveendran, R. Mukundan, "A comparative analysis of algorithms for fast computation of Zernike moments," Pattern Recognition, vol. 36, no. 3, pp. 731-742, March 2003. https://doi.org/10.1016/S0031-3203(02)00091-2