International Journal of Computer Vision

, Volume 1, Issue 4, pp 321–331

Snakes: Active contour models


  • Michael Kass
    • Schlumberger Palo Alto Research
  • Andrew Witkin
    • Schlumberger Palo Alto Research
  • Demetri Terzopoulos
    • Schlumberger Palo Alto Research

DOI: 10.1007/BF00133570

Cite this article as:
Kass, M., Witkin, A. & Terzopoulos, D. Int J Comput Vision (1988) 1: 321. doi:10.1007/BF00133570


A snake is an energy-minimizing spline guided by external constraint forces and influenced by image forces that pull it toward features such as lines and edges. Snakes are active contour models: they lock onto nearby edges, localizing them accurately. Scale-space continuation can be used to enlarge the capture region surrounding a feature. Snakes provide a unified account of a number of visual problems, including detection of edges, lines, and subjective contours; motion tracking; and stereo matching. We have used snakes successfully for interactive interpretation, in which user-imposed constraint forces guide the snake near features of interest.

Copyright information

© Kluwer Academic Publishers 1987