shape_index(image, sigma=1, mode='constant', cval=0)
The shape index, as defined by Koenderink & van Doorn , is a single valued measure of local curvature, assuming the image as a 3D plane with intensities representing heights.
It is derived from the eigen values of the Hessian, and its value ranges from -1 to 1 (and is undefined (=NaN) in flat regions), with following ranges representing following shapes:
.. table:: Ranges of the shape index and corresponding shapes.
=================== =============
Interval (s in ...) Shape
=================== =============
[ -1, -7/8) Spherical cup
[-7/8, -5/8) Through
[-5/8, -3/8) Rut
[-3/8, -1/8) Saddle rut
[-1/8, +1/8) Saddle
[+1/8, +3/8) Saddle ridge
[+3/8, +5/8) Ridge
[+5/8, +7/8) Dome
[+7/8, +1] Spherical cap
=================== =============
Input image.
Standard deviation used for the Gaussian kernel, which is used for smoothing the input data before Hessian eigen value calculation.
How to handle values outside the image borders
Used in conjunction with mode 'constant', the value outside the image boundaries.
Shape index
Compute the shape index.
>>> from skimage.feature import shape_indexSee :
... square = np.zeros((5, 5))
... square[2, 2] = 4
... s = shape_index(square, sigma=0.1)
... s array([[ nan, nan, -0.5, nan, nan], [ nan, -0. , nan, -0. , nan], [-0.5, nan, -1. , nan, -0.5], [ nan, -0. , nan, -0. , nan], [ nan, nan, -0.5, nan, nan]])
The following pages refer to to this document either explicitly or contain code examples using this.
skimage.feature.corner.shape_index
Hover to see nodes names; edges to Self not shown, Caped at 50 nodes.
Using a canvas is more power efficient and can get hundred of nodes ; but does not allow hyperlinks; , arrows or text (beyond on hover)
SVG is more flexible but power hungry; and does not scale well to 50 + nodes.
All aboves nodes referred to, (or are referred from) current nodes; Edges from Self to other have been omitted (or all nodes would be connected to the central node "self" which is not useful). Nodes are colored by the library they belong to, and scaled with the number of references pointing them