Geometric Computer Vision: Difference between revisions
No edit summary |
No edit summary |
||
| Line 6: | Line 6: | ||
See [[Convolutional neural network]]. | See [[Convolutional neural network]]. | ||
Traditionally, fixed filters are used instead of learned filters. | Traditionally, fixed filters are used instead of learned filters. | ||
==Edge Detection== | |||
Two ways to detect edges: | |||
* Difference operators | |||
* Models | |||
===Image Gradients=== | |||
* Angle is given by <math>\theta = \arctan(\frac{df}{dy}, \frac{df}{dx})</math> | |||
* Edge strength is given by <math>\left\Vert (\frac{df}{dx}, \frac{df}{dy}) \right\Vert</math> | |||
Revision as of 16:27, 2 February 2021
Notes for CMSC733 Classical and Deep Learning Approaches for Geometric Computer Vision taught by Prof. Yiannis Aloimonos.
Convolution and Correlation
See Convolutional neural network.
Traditionally, fixed filters are used instead of learned filters.
Edge Detection
Two ways to detect edges:
- Difference operators
- Models
Image Gradients
- Angle is given by \(\displaystyle \theta = \arctan(\frac{df}{dy}, \frac{df}{dx})\)
- Edge strength is given by \(\displaystyle \left\Vert (\frac{df}{dx}, \frac{df}{dy}) \right\Vert\)