This is an old revision of the document!
Table of Contents
Vision
Color Quantization
=References=
RGB cone
YUV polygon
HSV rectangle
Lab
Image segmentation
Floodfill
=References=
Watershed
=References=
Filters
=References=
Anti-noise
(smoothing) =References=
Median Filter
Vector Median Filter
Kuwahara filter
Peer Group Filtering
=References=
Anisotropic Filtering
Gradient
Prewitt
=Objective= Basic kernels for 1st order gradient. =Quick Def= Horizontal kernel :
| -1 | 0 | 1 |
|---|---|---|
| -1 | 0 | 1 |
| -1 | 0 | 1 |
Vertical kernel :
| -1 | -1 | -1 |
|---|---|---|
| 0 | 0 | 0 |
| 1 | 1 | 1 |
Roberts
=Objective=
=Quick Def= First kernel :
| 1 | 0 |
|---|---|
| 0 | -1 |
Second kernel :
| 0 | 1 |
|---|---|
| -1 | 0 |
Intensity :
I = sqrt(I1^2 + I2^2)
Direction :
theta = arctan(I2 / I1) + pi/4
Sobel
=Objective= Most popular 1st order kernels =Quick Def= Horizontal kernel :
| -1 | 0 | 1 |
|---|---|---|
| -2 | 0 | 2 |
| -1 | 0 | 1 |
Vertical kernel :
| -1 | -2 | -1 |
|---|---|---|
| 0 | 0 | 0 |
| 1 | 2 | 1 |
Intensity :
I = sqrt(Iv^2 + Ih^2)
Direction :
theta = arctan(Iv / Ih)
=Full Def=
The filter can be seen as the convolution of two filters.
Derivative :
| -1 |
|---|
| 0 |
| 1 |
Smoothing :
| 1 | 2 | 1 |
|---|
Laplace
=Objective= 2nd order kernel =Quick Def= Kernel :
| 0 | 1 | 0 |
|---|---|---|
| 1 | -4 | 1 |
| 0 | 1 | 0 |
Scharr
morphological
=References=
Dilation
Dilatation
Erosion
Erosion
Opening
Ouverture
Closing
Fermeture
Edge detection
Canny detector
=Objective= Best theoritical edge detector. =Quick Def= Noise filtering, gradient with horizontal vertical and diagonal kernels, thresholding with hysteresis taking into account the direction of the gradient.
