The Transactions of the Korea Information Processing Society (한국정보처리학회논문지)

Korea Information Processing Society (한국정보처리학회)
권호 표지

A Head Gesture Recognition Method based on Eigenfaces using SOM and PRL

SOM과 PRL을 이용한 고유얼굴 기반의 머리동작 인식방법

  • 이우진 (단국대학교 대학원 전산통계학과) ;
  • 구자영 (단국대학교 전산통계학과)
  • Published : 2000.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper a new method for head gesture recognition is proposed. A the first stage, face image data are transformed into low dimensional vectors by principal component analysis (PCA), which utilizes the high correlation between face pose images. The a self organization map(SM) is trained by the transformed face vectors, in such a that the nodes at similar locations respond to similar poses. A sequence of poses which comprises each model gesture goes through PCA and SOM, and the result is stored in the database. At the recognition stage any sequence of frames goes through the PCA and SOM, and the result is compared with the model gesture stored in the database. To improve robustness of classification, probabilistic relaxation labeling(PRL) is used, which utilizes the contextural information imbedded in the adjacent poses.

Keywords

References

  1. J. Yamato, J. Ohya, and K. Ishi, 'Recognizing Human Action in Time-Sequential Images Using Hidden Markov Model,' IEEE Computer Society Conference on CVPR, Vol.1, w.379-385, June 1992 https://doi.org/10.1109/CVPR.1992.223161
  2. Carlos Morimoto, Yaser Yacoob, Larry Davis, 'Recognition of Head Gestures Using Hidden Markov Models,' International Conference on Pattern Recognition, Austria, pp.461-465, 1996
  3. Andrew D. Wilson, Aaron F. Bobick, 'Recognition and Interpretation of Parametric Gesture,' M.I.T Media Lab. TR No.421 , 1998
  4. R. J. T. Mrris, L. D. Rubin and H. Tirri, 'Neural Network Techniques for Object Orientation Detection: Solution by Optimal Feedforward Network and Learning Vector Quantization Approaches,' IEEE Trans. on PAMI, Vol.2, No.11, pp.1107-1114, Nov. 1990 https://doi.org/10.1109/34.61712
  5. E. Littmann, A. Drees, and H. Ritter, 'Visual gesturebased robot guidance with a modular neural system,' NIPS1995(Poster), Denver, Colorado, USA, November 1995
  6. Enno Littmann, Andrea Drees, and Helge Ritter, 'Visual Gesture Recognition by a Modular Neural System,' Proceedings ICNN'96(W. v. Seelen, Chr. v.d. Malsburg, eds), Springer 1996
  7. Andrew Wilson, Aaron Bobick, 'Using Configuration States for the Representation and Recognition of Gesture,' M.I.T Media Lab. TR No.308, 1995
  8. Trevor J. Darrell, Irfan A. Essa, Alex P. Pentland, 'Task-specific Gesture Analysis in Real-Time using Interpolated Views,' M.I.T Media Lab. TR No.364, 1995
  9. A. F. Bobick and A. D. Wilson, 'A State-Based Approach to the Representation and Recognition of Gesture,' IEEE Trans. on PAMI, Vol.9, No.12, pp.1325-1337, Dec. 1997 https://doi.org/10.1109/34.643892
  10. Teuvo Kohonen, 'The 'Neural' Phonetic Typewriter,' IEEE Computer, pp.11-22, Mar. 1988 https://doi.org/10.1109/2.28
  11. A. Rosenfeld, R. Hummel, Zucker, 'Scene labeling by relaxation algoritms', IEEE Trans. Syst., Man, Cyben., Vol.SMC-6, pp.420-433, 1976
  12. DL Waltz, 'Understanding line drawings of scenes with shadows,' In The Psychology of Computer Vision, McGraw-Hill, New York, 1957
  13. M. Kirby and L. Sirovich, 'Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces,' IEEE Trans. on PAMI, Vol.12, No.1, pp.103-107, Jan. 1990 https://doi.org/10.1109/34.41390
  14. James A. Freeman, David M. Skapura, 'Neural Networks Algorithms, Applications, and Programming Techniques,' Addison-Wesley Publishing Componay, Inc. 1991