Journal of KIISE:Computing Practices and Letters (한국정보과학회논문지:컴퓨팅의 실제 및 레터)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Hand Gesture Interface Using Mobile Camera Devices

모바일 카메라 기기를 이용한 손 제스처 인터페이스

  • 이찬수 (영남대학교 전자공학과) ;
  • 천성용 (영남대학교 전자공학과) ;
  • 손명규 (대구경북과학기술원 미래산업융합기술연구부) ;
  • 이상헌 (대구경북과학기술원 미래산업융합기술연구부)
  • Received : 2009.12.24
  • Accepted : 2010.02.22
  • Published : 2010.05.15
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a hand motion tracking method for hand gesture interface using a camera in mobile devices such as a smart phone and PDA. When a camera moves according to the hand gesture of the user, global optical flows are generated. Therefore, robust hand movement estimation is possible by considering dominant optical flow based on histogram analysis of the motion direction. A continuous hand gesture is segmented into unit gestures by motion state estimation using motion phase, which is determined by velocity and acceleration of the estimated hand motion. Feature vectors are extracted during movement states and hand gestures are recognized at the end state of each gesture. Support vector machine (SVM), k-nearest neighborhood classifier, and normal Bayes classifier are used for classification. SVM shows 82% recognition rate for 14 hand gestures.

본 논문에서는 스마트 폰, PDA와 같은 모바일 장치에 있는 카메라 기기를 이용한 손동작 제스처 인터페이스를 위한 손 움직임 추적 방법을 제안하고 이를 바탕으로 한 손 제스처 인식 시스템을 개발한다. 사용자의 손동작에 따라 카메라가 움직임으로써, 전역 optical flow가 발생하며, 이에 대한 우세한 방향 성분에 대한 움직임만 고려함으로써, 노이즈에 강인한 손움직임 추정이 가능하다. 또한 추정된 손 움직임을 바탕으로 속도 및 가속도 성분을 계산하여 동작위상을 구분하고, 동작상태를 인식하여 연속적인 제스처를 개별제스처로 구분한다. 제스처 인식을 위하여, 움직임 상태에서의 특징들을 추출하여, 동작이 끝나는 시점에서 특징들에 대한 분석을 통하여 동작을 인식한다. 추출된 특징점을 바탕으로 제스처를 인식하기 위하여 SVM(Support vector machine), k-NN(k-nearest neighborhood classifier), 베이시안 인식기를 사용했으며, 14개 제스처에 대한 인식률은 82%에 이른다.

Keywords

References

  1. H. Sung, H. Byun, "3D face tracking using MLESAC motion estimation based particle filter," Proc. of the KIISE Fall Congress 2009, vol.36, no.2(A), pp.214- 215, 2009. (in Korean)
  2. J. Lim, S. Kim, C. Lee, G. S. Lee, H. J. Yang, E. M. Lee, "Cursive Script Recognition in Wine Label Images Using Over-Segmentation and Character Combination Filtering," Proc. of the KIISE Fall Congress 2009, vol.36, no.2(A), pp.222-223, 2009. (in Korean)
  3. S. Mitra, T. Acharya, "Gesture Recognition: A survey," IEEE Trans. Systems, Man and Cybernetics-Part C, vol.37, no.3, pp.311-324, May 2007.
  4. M. Rohs, "Real-World Interaction with Camera- Phones," Ubiquitous Computing Systems, LNCS, vol.3598, pp.74-89, 2005.
  5. S. Winkler, K. Rangaswamy, Z.Y. Zhou, "Intuitive user interface for mobile devices based on visual motion detection," Proc. SPIE, Multimedia on Mobile Device, vol.6507, pp.65070V, 2007.
  6. J. Hwang, G. J. Kim, N. Kim, "Camera based relative motion tracking for hand-held virtual reality," In Proc. NICOGRAPH International, 2006.
  7. M Barnard, J. Hannuksela, P. Sangi, J. Heikkila, "A vision based motion interface for mobile phones," In Proc. of International Conference on Computer Vision Systems, 2007.
  8. A. Haro, K. Mori, T. Capin, S. Wilkinson, "Mobile camera-based user interaction," LNCS 3766, Computer Vision in Human-Computer Interaction, pp.79-89, 2005.
  9. M. S. Ko, K. H. Lee, C. W. Kim, J. H. Ahn, I. J. Kim, "An Implementation of User Interface Using Vision-based Gesture Recognition," Proc. of the KIISE Korea Computer Congress, vol.35, no.1(C), pp.507-511, 2008.
  10. J. Shi and C. Tomasi, "Good feature to track," In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp.594-600, June 1994.
  11. B. D. Lucas and T. Kanade, "An iterative image registration technique with an application to stereo vision," In Proc. Image Understanding Workshop, pp.121-130, 1981.
  12. A. Kendon, "Gesticulation and speech: two aspects of the process of utterance," The relationship between verbal and nonverbal communication, pp.207-227, 1980.
  13. Chan-Su Lee, Gyu-tae Park, Jong-Sung Kim, Zeungnam Bien, Won Jang, Sung-Kwon Kim, "Real-time Recognition System of Korean Sign Language based on Elementary Components," IEEE FUZZ'97, pp.1463- 1468, 1997.