Active contour segmentation¶
Takes a starting contour (snake) and uses active contours to optimise its shape. Takes a table(s) with coordinates of the initial contour, returns a table(s) with coordinates of optimised contour.
Definition¶
Input ports¶
- source image
Source image
- contours table
Starting contour
Output ports¶
- result table
Resulting contour
Configuration¶
- X or R column (X)
Column names with contour X coordinates
- Y or C column (Y)
Column names with contour Y coordinates
- Length parameter (alpha)
Snake length shape parameter. Higher values makes snake contract faster.
- Smoothness parameter (beta)
Snake smoothness shape parameter. Higher values makes snake smoother.
- Boundary condition (boundary_condition)
Boundary conditions for worm (first and last point). Periodic attaches the two ends, fixed holds them in place and free allows them to move.
- Convergence (convergence)
Convergence criteria.
- Coordinates type (coordinates)
Coordinate tpes for the input columns
- Gamma parameter (gamma)
Controls attraction to edges. Use negative values to repel snake from edges.
- Max iterations (max_iterations)
Maximum number of iterations
- Max move (max_px_move)
Maximum distance in number of pixels to move per iteration.
- Edge parameter (w_edge)
Controls attraction to edges. Use negative values to repel snake from edges.
- Brightness parameter (w_line)
Controls attraction to brightness. Use negative values to attract to dark regions.
Examples¶
Implementation¶
- class node_contours.ActiveContourSegmentation[source]