Convolutional Matrix Kernel Function: Difference between revisions
Jump to navigation
Jump to search
(Created page with "A Convolutional Matrix Kernel Function is a convolution operator that is a small matrix. * <B>AKA:</B> Kernel Mask. * <B>Example(s):</B> ** an Identity Convo...") |
m (Text replacement - "\<P\>([\s]{1,7})([^\s])" to "<P> $2") |
||
(16 intermediate revisions by 3 users not shown) | |||
Line 1: | Line 1: | ||
A [[Convolutional Matrix Kernel Function]] is a [[ | A [[Convolutional Matrix Kernel Function]] is a [[convolutional kernel function]] that is a [[matrix function]]. | ||
* <B>AKA:</B> [[Kernel Mask]]. | * <B>AKA:</B> [[Convolutional Matrix Kernel Function|Kernel Mask]]. | ||
** … | |||
* <B>Example(s):</B> | * <B>Example(s):</B> | ||
** a [[3x3 Convolution Matrix Filter]]. | |||
** a [[5x5 Convolution Matrix Filter]]. | |||
** an [[Identity Convolution Matrix]], such as <math> \begin{bmatrix} 0 & 0 & 0 \\ 0 & 1 & 0 \\ 0 & 0 & 0 \end{bmatrix} </math> | ** an [[Identity Convolution Matrix]], such as <math> \begin{bmatrix} 0 & 0 & 0 \\ 0 & 1 & 0 \\ 0 & 0 & 0 \end{bmatrix} </math> | ||
** an [[Edge Detection Convolution Matrix]], such as <math> \begin{bmatrix} -1 & -1 & -1 \\ -1 & \ \ 8 & -1 \\ -1 & -1 & -1 \end{bmatrix} </math> | ** an [[Edge Detection Convolution Matrix]], such as <math> \begin{bmatrix} -1 & -1 & -1 \\ -1 & \ \ 8 & -1 \\ -1 & -1 & -1 \end{bmatrix} </math> | ||
Line 10: | Line 13: | ||
** any [[Convolution Graph Kernel Function]]. | ** any [[Convolution Graph Kernel Function]]. | ||
* <B>See:</B> [[Image Processing]], [[Convolutional Neural Network]]. | * <B>See:</B> [[Image Processing]], [[Convolutional Neural Network]]. | ||
---- | ---- | ||
---- | ---- | ||
==References== | |||
== References == | |||
=== 2017 === | |||
* (Wikipedia, 2017) ⇒ https://en.wikipedia.org/wiki/Kernel_(image_processing) Retrieved:2017-6-27. | |||
** In [[image processing]], a '''kernel''', '''convolution matrix''', or '''mask''' is a small [[Matrix (mathematics)|matrix]]. It is used for blurring, sharpening, embossing, [[edge detection]], and more. This is accomplished by doing a [[Kernel (image processing)#Convolution|convolution]] between a kernel and an [[Bitmap image|image]]. | |||
=== 2015 === | === 2015 === | ||
* (Wikipedia, 2015) | * (Wikipedia, 2015) ⇒ http://en.wikipedia.org/wiki/Kernel_(image_processing)#Details Retrieved:2015-11-7. | ||
** Depending on the element values, a kernel can cause a wide range of effects. <P> The above are just a few examples of effects achievable by convolving kernels and images. | |||
** Depending on the element values, a kernel can cause a wide range of effects. | |||
---- | ---- | ||
__NOTOC__ | |||
[[Category:Concept]] | [[Category:Concept]] | ||
Latest revision as of 04:38, 18 August 2021
A Convolutional Matrix Kernel Function is a convolutional kernel function that is a matrix function.
- AKA: Kernel Mask.
- …
- Example(s):
- a 3x3 Convolution Matrix Filter.
- a 5x5 Convolution Matrix Filter.
- an Identity Convolution Matrix, such as [math]\displaystyle{ \begin{bmatrix} 0 & 0 & 0 \\ 0 & 1 & 0 \\ 0 & 0 & 0 \end{bmatrix} }[/math]
- an Edge Detection Convolution Matrix, such as [math]\displaystyle{ \begin{bmatrix} -1 & -1 & -1 \\ -1 & \ \ 8 & -1 \\ -1 & -1 & -1 \end{bmatrix} }[/math]
- an Image Sharpening Convolution Matrix, such as [math]\displaystyle{ \begin{bmatrix} \ \ 0 & -1 & \ \ 0 \\ -1 & \ \ 5 & -1 \\ \ \ 0 & -1 & \ \ 0 \end{bmatrix} }[/math]
- Counter-Example(s):
- See: Image Processing, Convolutional Neural Network.
References
2017
- (Wikipedia, 2017) ⇒ https://en.wikipedia.org/wiki/Kernel_(image_processing) Retrieved:2017-6-27.
- In image processing, a kernel, convolution matrix, or mask is a small matrix. It is used for blurring, sharpening, embossing, edge detection, and more. This is accomplished by doing a convolution between a kernel and an image.
2015
- (Wikipedia, 2015) ⇒ http://en.wikipedia.org/wiki/Kernel_(image_processing)#Details Retrieved:2015-11-7.
- Depending on the element values, a kernel can cause a wide range of effects.
The above are just a few examples of effects achievable by convolving kernels and images.
- Depending on the element values, a kernel can cause a wide range of effects.