DOI QR코드

DOI QR Code

Multiple Face Segmentation and Tracking Based on Robust Hausdorff Distance Matching

  • Published : 2003.06.01

Abstract

This paper describes a system for tracking multiple faces in an input video sequence using facial convex hull based facial segmentation and robust hausdorff distance. The algorithm adapts skin color reference map in YCbCr color space and hair color reference map in RGB color space for classifying face region. Then, we obtain an initial face model with preprocessing and convex hull. For tracking, this algorithm computes displacement of the point set between frames using a robust hausdorff distance and the best possible displacement is selected. Finally, the initial face model is updated using the displacement. We provide an example to illustrate the proposed tracking algorithm, which efficiently tracks rotating and zooming faces as well as existing multiple faces in video sequences obtained from CCD camera.

Keywords

References

  1. Yang, G.Z., Huang, T.S.: 'Human face detection in acomplex background' , Patten Recognition., 1994, 27,(1), pp. 43-63
  2. Miao, J., Yin, B., Wang, K., Shen, L., Chen, X.: 'Ahierarchical multiscale and multiangle system for humanface detection in a complex background usinggravity-center template' , Pattem Recognition, 1999, 32,(7), pp. 1237-1248 https://doi.org/10.1016/S0031-3203(98)00156-3
  3. Rowley, H.A., Baluja, S., Kanade, T.: 'Neuralnetwork-based face detection' , IEEE Trans. PattenAnal. Mach. Intell. 1998, 20, (1), pp. 23-38 https://doi.org/10.1109/34.655647
  4. Sung, K. K., Poggio, T.: 'Example-based learning forview-based human face detection' , IEEE Trans. Pattem Anal. Mach. Intell. 1998, 20, (1),pp. 39-51 https://doi.org/10.1109/34.655648
  5. Lee, C. H., Kim, J.S., Park, K.H.: 'Automatic humanface location in a complex background using motionand color information' , Pattern Recognition, 1996, 29,(11), pp. 129-140
  6. Sobottka, K., Pitas, I.: 'A novel method for automaticface segmentation, facial feature extraction and tracking' , Signal Process, Image Commun., 1998, 12, (3),pp. 263-281 https://doi.org/10.1016/S0923-5965(97)00042-8
  7. Wu, H., Chen, Q., Yachida, M.: Face detection from color images using a fuzzy pattern matching method, IEEE Trans. Pattem Anal. Mach. Intell., 1999, 21, (6),pp. 557-563 https://doi.org/10.1109/34.771326
  8. Garcia, C., Tziritas, G.: 'Face detection using quantizedskin color regions merging and wavelet packet analysis' , IEEE Trans. Multimedia, 1999, 1, (3), pp. 264-277 https://doi.org/10.1109/6046.784465
  9. Chi, D., Ngan, K.N.: 'Face Segmentaion Using kin-CoIor map in Videophone Applications, IEEETrans. Circuits and systems for video technology', June,1999, 9, (4), PP. 551-564 https://doi.org/10.1109/76.767122
  10. McKenna, S.J., Gong, S., Wurtz, R., Banin, D., Tanner,,J.: 'Tracking facial feature points with gabor waveletsand shape models' , Proceedings of the firstInternational Conference on Audio and Video Based Biometric Person Authentication, Crans-Montana,Swotzerland, March 1997, Springer, Computer Science,Vol, 1206, pp.35-42
  11. Qian, R., Sezan, M.I., Matthews, K.E.: 'A robustreal-time face tracking algorithm', Processing of the IEEE International Conference on Image Processing, ICIP-98, Chicago, USA, 1998, pp. 131-135
  12. Pardas, M., Sayrol, E.: 'Tracking of contourscombining snakes with motion estimation' , Proceding of the IEEE International Conference on ImageProcessing, ICIP-OO, Vancouver, Canada, September2000, pp. TA07.14
  13. Huttenlocher, D. P., Klanderman, G. A., Rucklidge W.J.: 'Comparing Images Using the HaudorfF distance' ,IEEE. Trans. Pattem Anal. Machine. Intelligence 1999, 15, (9), pp. 850-863
  14. Hussain, Z.: ' Digital Image Processing' , ELLISHORWOOD LIMITED in New York in London
  15. Sim, D., Kwon, O.: 'Rae-Hong Parlc, Object MatchingAlgorithms Using Robust HausdorfT Distance Measures' . , IEEE Trans. Image Processing, March, 1999, 8,(3), pp. 425-429 https://doi.org/10.1109/83.748897
  16. Huttenlocher, D.P., Klanderman, G. A., Rucklidge, W.J.:'Comparing Images Using the Hausdorff Distance' ,IEEE Trans. Pattem Analysis and Machine intelligence, Sep, 1993, 12, (9), pp. 850-863