Today, we will learn about how to define boundaries.
What are the object boundaries?
This picture would be Human annotated boundaries.
By using Edge Detection technique, we can get this kind of edge.
By using multi-scale edge detection, we can get this picture.
Edge strength does not necessarily correspond to our perception of boundaries.
These are pictures we can feel more gap between human annotated boundaries and edge detection.
Defining boundaries are hard for us too.
This edge detection technique is being applied to many areas.
In next class, we will learn about line parameterizations.
'AI > Computer Vision Materials' 카테고리의 다른 글
| 5.2 Hough Transform (0) | 2020.08.05 |
|---|---|
| 5.1 Lines Parameterization (0) | 2020.08.05 |
| 4.1 Filtering vs Convolution (0) | 2020.08.05 |
| 4.0 Image Gradients and Gradient Filtering (0) | 2020.08.04 |
| 3.1 Image Pyramid (0) | 2020.08.03 |
