Gaussian Pyramid

Perform Gaussian pyramid decomposition

• 

Libraries:
Computer Vision Toolbox / Transforms

Description

The Gaussian Pyramid block computes Gaussian pyramid reduction or expansion to resize an image. The image reduction process involves lowpass filtering and then downsampling the image pixels. The image expansion process involves upsampling and then lowpass filtering the image pixels. You can also use this block to build a Laplacian pyramid.

Examples

Construct Laplacian Pyramid Image

Construct a Laplacian pyramid image.

• Open Script

Ports

Input

I — Input image

scalar | vector | matrix | array

Input image, specified as a scalar, a vector, an M-by-N matrix, or an M-by-N-by-C array. C is the number of color channels in the input image. To specify this input as a scalar or vector, you must set the Operation parameter to Expand.

Data Types: single | double | int8 | int16 | int32 | uint8 | uint16 | uint32 | fixed point

Output

Port_1 — Output image

scalar | vector | matrix | array

Output image, returned as a scalar, a vector, a matrix, or an array. The dimensions of the output image are determined by the Operationand Pyramid level parameter values. For this port to return a scalar or vector, you must set the Operation parameter to Reduce.

Data Types: single | double | int8 | int16 | int32 | uint8 | uint16 | uint32 | Boolean | fixed point

Parameters

Operation — Select operation

Reduce (default) | Expand

Select the Gaussian pyramid operation as one of these methods:

• Reduce — The block applies a lowpass filter and then downsamples the input image.

• Expand — The block upsamples and then applies a lowpass filter to the input image.

Pyramid level — Image scaling factor

1 (default) | positive integer

Specify the factor of 2 by which to upsample or downsample each dimension of the image.

For an M-by-N input image, if you set the Operation parameter to Reduce and the Pyramid level to 1, the dimensions of the output image are ceil(M/2)-by-ceil(N/2).

For an M-by-N input image, if you set the Operation parameter to Expand, the dimensions of the output image are [(M-1)2^l+1]-by-[(N-1)2^l+1], where the Pyramid level parameter l must be a positive integer.

Coefficient source — Lowpass filter coefficient source

Default separable filter [1/4-a/2 1/4 a 1/4 1/4-a/2] (default) | Specify via dialog

Specify the lowpass filter coefficient source as Default separable filter [1/4-a/2 1/4 a 1/4 1/4-a/2] or Specify via dialog.

Coefficients for separable filter — Separable filter coefficient

[0.0625 0.25 0.375 0.25 0.0625] (default) | vector

Specify the separable filter coefficients as a vector.

Hidden coefficients — Hidden separable filter coefficients

[1/4-0.375/2 1/4 0.375 1/4 1/4-0.375/2] (default) | vector

Specify the hidden separable filter coefficients as a vector.

Block Characteristics

Data Types	double | fixed point | integer | single
Multidimensional Signals	yes
Variable-Size Signals	yes

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using Simulink® Coder™.

Version History

Introduced before R2006a