CannyEdgeDetector
Module that applies the Canny edge detector to an image. This edge detector works in five steps: 1. Gradient Estimation using a Gaussian edge detector. 2. Orientation Classification. 3. Nonmaximum Supression. 4. Hysteresis Thresholding. This is not exactly the algorithm as described by Canny (the edge filter is different and edges are only found at a single scale) but it is reasonably similar.
Example XML definition
A simple example
<module
class = "CannyEdgeDetector"
name = "CannyEdgeDetector"
/>
Parameters
| Name | Description | Type | Default |
|---|---|---|---|
| class | The class name for the module; must be "CannyEdgeDetector". | string | |
| name | The name of this instance of the module. | string | |
| scale | Scale parameter | float | |
| T0 | First threshold | float | |
| T1 | Second threshold | float | |
| T2 | Third threshold | float |
Module Connections
Inputs
| Name | Description |
|---|---|
| INPUT | The iage input |
Outputs
| Name | Description |
|---|---|
| EDGES | Edge magnitude |
| MAXIMA | Orientation estimate |
| OUTPUT | Final edges |
| dx | Gradient estimation and categorization |
| dy | Gradient estimation and categorization |
| dGx | Filter kernel |
| dGy | Filter kernel |
Author
Christian Balkenius
christian.balkenius@lucs.lu.se
Lund University Cognitive Science
Files
CannyEdgeDetector.h
CannyEdgeDetector.cc
CannyEdgeDetector.ikc