Convolutional Matrix Kernel Function

A Convolutional Matrix Kernel Function is a convolution operator that is a small matrix.

• AKA: Kernel Mask.
• Example(s):
  • 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):
  • a Convolution String Kernel Function.
  • any Convolution Tree Kernel Function.
  • any Convolution Graph Kernel Function.
• See: Image Processing, Convolutional Neural Network.

---

---

References

2015

• (Wikipedia, 2015) ⇒ http://en.wikipedia.org/wiki/Kernel_(image_processing) Retrieved:2015-11-7.
  • In image processing, a kernel, convolution matrix, or mask is a small matrix useful for blurring, sharpening, embossing, edge-detection, and more. This is accomplished by means of convolution between a kernel and an image.
• (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.

---