The Application of an Active Contour Method for Extracting Human Face Contour

The active contour is an effective method to perform image segmentation. But its key technology problem is, both the establishment of a mathematic model and the development of the calculating algorithm are excessively dependent on the initial contour position. In dynamic image analysis, the difference method and the fast template matching algorithm provide available solutions for dealing with the problem of sensitivity to initial position in active contour method. In this paper, the initial position of human body was first tested by using difference operation of dynamic image sequence and binary. Then the face position was initially located by fast template matching algorithm. And finally, the face position was located by active contour algorithm of “balloon” model to extract the face contour.

[1]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[2]  Shinichiro Omachi,et al.  Fast Template Matching With Polynomials , 2007, IEEE Transactions on Image Processing.

[3]  Ayman El-Baz,et al.  Automatic Detection and Recognition of Lung Abnormalities in Helical CT Images Using Deformable Templates , 2004, MICCAI.

[4]  Mubarak Shah,et al.  A Fast algorithm for active contours and curvature estimation , 1992, CVGIP Image Underst..

[5]  Ramesh C. Jain,et al.  Using Dynamic Programming for Solving Variational Problems in Vision , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Anthony J. Yezzi,et al.  Sobolev Active Contours , 2005, International Journal of Computer Vision.

[7]  Taein Lee,et al.  Active contour models , 2005 .

[8]  Ahmet M. Kondoz,et al.  An efficient scalable object contour tracking scheme and its application for video segmentation , 2004, IEEE 6th Workshop on Multimedia Signal Processing, 2004..