linemodel

LineModel

class skimage.measure.LineModel [source]

Bases: skimage.measure.fit.BaseModel

Total least squares estimator for 2D lines.

Lines are parameterized using polar coordinates as functional model:

dist = x * cos(theta) + y * sin(theta)

This parameterization is able to model vertical lines in contrast to the standard line model y = a*x + b.

This estimator minimizes the squared distances from all points to the line:

min{ sum((dist - x_i * cos(theta) + y_i * sin(theta))**2) }

A minimum number of 2 points is required to solve for the parameters.

Deprecated class. Use LineModelND instead.

Attributes

params

(tuple) Line model parameters in the following order dist, theta.

__init__() [source]

estimate(data) [source]

Estimate line model from data using total least squares.

Parameters:	data : (N, 2) array N points with (x, y) coordinates, respectively.
Returns:	success : bool True, if model estimation succeeds.

predict_x(y, params=None) [source]

Predict x-coordinates using the estimated model.

Parameters:	y : array y-coordinates. params : (2, ) array, optional Optional custom parameter set.
Returns:	x : array Predicted x-coordinates.

predict_y(x, params=None) [source]

Predict y-coordinates using the estimated model.

Parameters:	x : array x-coordinates. params : (2, ) array, optional Optional custom parameter set.
Returns:	y : array Predicted y-coordinates.

residuals(data) [source]

Determine residuals of data to model.

For each point the shortest distance to the line is returned.

Parameters:	data : (N, 2) array N points with (x, y) coordinates, respectively.
Returns:	residuals : (N, ) array Residual for each data point.