[mmlabelflat] [Up] [mmstats] Measurements

mmpatspec
Pattern spectrum (also known as granulometric size density).

Synopsis

h = mmpatspec( f, type = 'OCTAGON', n = 65535, Bc = None, Buser = None )

Implemented in Python.

Input

f Image Binary image.
type String

Disk family: 'OCTAGON', 'CHESSBOARD', 'CITY-BLOCK', 'LINEAR-V', 'LINEAR-H', 'LINEAR-45R', 'LINEAR-45L', 'USER'.

Default: 'OCTAGON'

n Double

Maximum disk radii.

Default: 65535

Bc Structuring Element

Connectivity for the reconstructive granulometry. Used if '-REC' suffix is appended in the 'type' string.

Default: None (3x3 elementary cross)

Buser Structuring Element

User disk, used if 'type' is 'USER'.

Default: None (3x3 elementary cross)

Output

h Image Gray-scale (uint8 or uint16) or binary image.

a uint16 vector.

Description

Compute the Pattern Spectrum of a binary image. See Mara:89b. The pattern spectrum is the histogram of the open transform, not taking the zero values.

Equation

Source Code

def mmpatspec(f, type='OCTAGON', n=65535, Bc=None, Buser=None):
    if Bc is None: Bc = mmsecross()
    if Buser is None: Buser = mmsecross()
    assert mmisbinary(f),'Error: input image is not binary'
    g=mmopentransf(f,type,n,Bc,Buser)
    h=mmhistogram(g)
    h=h[1:]
    return h

See also

mmopen Morphological opening.
mmopentransf Open transform.
mmsedisk Create a disk or a semi-sphere structuring element.
[mmlabelflat] [Up] [mmstats] Python
Copyright (c) 2003, Roberto A. Lotufo, UNICAMP-University of Campinas; Rubens C. Machado, CenPRA-Renato Archer Research Center.