Image scattering feature matrix
returns the scattering feature matrix for the wavelet image scattering network,
smat = featureMatrix(
sf, and the input image,
im is a real-valued 2-D
(M-by-N) or 3-D matrix
im is a 3-D
matrix, the size of the third dimension must be 3. If
im is a 2-D
Np is the number of scattering paths and
Ms-by-Ns is the resolution of the scattering
im is a 3-D matrix,
applies the transformation specified by
smat = featureMatrix(___,'Transform',
transformtype to the scattering
coefficients. Valid options for
'none'. If unspecified,
transformtype defaults to
'none'. You can use this
syntax with any of the previous syntaxes.
Obtain Feature Matrix for Wavelet Image Scattering Network
This example shows how to obtain the feature matrix for a wavelet image scattering network.
xbox image. Create an image scattering network suitable for the image.
load xbox sf = waveletScattering2('ImageSize',size(xbox))
sf = waveletScattering2 with properties: ImageSize: [128 128] InvarianceScale: 64 NumRotations: [6 6] QualityFactors: [1 1] Precision: "single" OversamplingFactor: 0 OptimizePath: 1
Obtain the feature matrix.
smat = featureMatrix(sf,xbox);
sf — Wavelet image scattering network
Wavelet image scattering network, specified as a
im — Input image
Input image, specified as real-valued 2-D matrix or 3-D matrix. If
im is 3-D,
im is assumed to be a color image
in the RGB color space, and the size of the third dimension must equal 3. The row and
column sizes of
im must match the
sc — Scattering coefficients
Scattering coefficients, specified as a cell array.
obtained from the
scatteringTransform method of the image scattering network.
transformtype — Transformation
'none' (default) |
Transformation to apply to the scattering coefficients:
'none': No transformation is applied to the scattering coefficients.
'log': The natural logarithm is applied to the scattering coefficients.
smat — Scattering feature matrix
Introduced in R2019a