Snake: introductory study and experiments






    June 2000 through May 9, 2001:

  • So far, the paper Gradient vector flow: a new external force for snake was reviewed, files downloaded from the net, which are running under Matlab.
  • The experiments have been made applying the close snake on the default images: 110.pgm and T1sax120.pgm. The results show that there are failures with GVF that snake cannot fit the boundaries; however, such edges or boundaries are clearly distinguishable by user.
  • To verify the accuracy of this snake algorithm, a black and white image similar to the skull boundary in T1sax120.pgm, was created and the snake fit the boundaries accurately.


    May 10, 2001:

  • The number of iterations for GVF was of interest. For that reason three numbers were applied on head2.pgm: 30, 80 and 150. Results show that the only difference is in the width of total arrows, showing the gradient vector flow, which gets bigger with increasing the iteration number. There were no other results observed by applying different numbers of iteration.


    Back