Lip Contour Extraction Using Active Shape Model Based on Energy Minimization

에너지 최소화 기반 능동형태 모델을 이용한 입술 윤곽선 추출

  • 장경식 (동의대학교 멀티미디어공학과)
  • Published : 2006.10.31

Abstract

In this paper, we propose an improved Active Shape Model for extracting lip contour. Lip deformation is modeled by a statistically deformable model based Active Shape Model. Because each point is moved independently using local profile information in Active Shape Model, many error may happen. To use a global information, we define an energy function similar to an energy function in Active Contour Model, and points are moved to positions at which the total energy is minimized. The experiments have been performed for many lip images of Tulip 1 database, and show that our method extracts lip shape than a traditional ASM more exactly.

이 논문에서는 능동형태 모델을 개선하여 입술의 형태를 효과적으로 추출하는 방법을 제안하였다. 입술의 형태변형은 능동형태 모델에 기반을 둔 통계적 형태 변형 모델을 사용하여 표현하였다. 능동형태 모델에서 각 점은 지엽적인 정보인 프로파일을 기반으로 독립적으로 이동하기 때문에 많은 오류가 발생할 수 있다. 전역적인 정보를 사용하기 위하여 이 논문에서는 능동윤곽선 모델에서 사용하는 것과 유사한 에너지 함수를 정의하고 전체 에너지가 최소화되는 위치로 점들이 이동하게 하였다. Tulip 1 데이터 베이스에 있는 입술 영상을 대상으로 실험한 결과, 제안한 방법이 기존 방법보다 실제 형태에 가깝게 입술을 추출하였다.

Keywords

References

  1. Yang J., R. Stiefelhagen, U. Meier and A. Waibel, 'Real-time Face and Facial Feature Tracking and Application,' Proceedings of Auditory-Visual Speech Processing, pp. 79-84, 1998
  2. Kaucic R., A. Blake, 'Accurate, Real-Time, Unadorned Lip Tracking,' Proceedings of the 6th International Conf. on Computer Vision, pp. 370-375, 1998
  3. Oliver N., A. Pentland, 'LAFTER: Lips and Face Real Time Tracker,' Proceedings of the 1997 Conf. on Computer Vision and Pattern Recognition, pp. 123-129, 1997
  4. Wark T., Sridharan and V. Chandran, 'An Approach to Statistical Lip Modelling for Speaker Identification via Chromatic Feature Extraction,' Proceedings of the 14th International Conf. on Pattern Recognition, Vol. 1, pp. 123-125, 1998
  5. Basu S., N. Oliver and A. Pentlan, '3D Modeling and Tracking of Human Lip Motions,' Proceedings of the 6th International Conf. on Computer Vision, pp. 337-343, 1998
  6. Delmas P., Y. Coulon and V. Fristot, 'Automatic Snakes for Robust Lip Boundaries Extraction,' IEEE International Conf. on. Acoustics, Speech and Signal Processing, Vol. 6, pp. 3069-3072, 1999
  7. Lievin M., F. Luthon, 'Unsupervised Lip Segmentation under Natural Conditions,' IEEE International Conf. on Acoustics, Speech and Signal Processing, Vol. 6, pp. 3065-3068, 1999
  8. Luettin J., N. A. Thacker and S. W. Beet, 'Locating and Tracking Facial Speech Features,' Proceedings of The International Conf. on Pattern Recognition, pp. 652-656, 1996
  9. Iain Matthnews, Timothy F. Cootes, J. Andrew Banghan, Stephen Cox and Richard Marvey, 'Extraction of Visual Features for Lipreading,' IEEE Tans. on Pattern Recognition and Machine Analysis, Vol. 24, No. 2, pp. 198-213, Feb., 2002 https://doi.org/10.1109/34.982900
  10. Donna J. Williams and Mubarak Shah, 'A Fast Algorithm for Active Contour and Curvature Estimation,' CVGIP:Image Understanding, Vol. 55, No. 1, pp. 14-26, 1992 https://doi.org/10.1016/1049-9660(92)90003-L
  11. M. B. Stegmann, R. Fisker, 'On Properties of Active Shape Models,' Informatics and Mathematical Modelling, Technical University of Denmark, 2000
  12. Movellan J. R., 'Visual Speech Recognition with Stochastic Networks,' Advances in Neural Information Processing System. Vol. 7, MIT Press Cambridge, 1995