Figure: Tiny black dots represent initial position of the snake. The snake will be attracted towards the surface of the white circle

CSC I1896: Computer Vision, Fall 2002

The City College of
The City University of New York

Instructor: Dr. Sam Fenster, Assitant Professor, The City College of CUNY

Student: Uttam Kumar Majumder

The City College of The City University of New York

"Detecting object from Image using ‘deformable contour’, or ‘active contour’, or ‘snake’ "

Abstract: A snake can be defined as a set of points. Given an image I and a set of points P1, P2, P3, …Pn representing the initial position of the deformable contour, we have to find a deformable contour P1', P2', P3'....Pn' which fits the target image contour best (that is the interesting image feature we are looking for).

Some output images