CV Chapter 3 Segmentation
Questions about the lecture 'Computer Vision' of the RWTH Aachen Chapter 3 Segmentation
Questions about the lecture 'Computer Vision' of the RWTH Aachen Chapter 3 Segmentation
Kartei Details
| Karten | 53 |
|---|---|
| Sprache | English |
| Kategorie | Informatik |
| Stufe | Universität |
| Erstellt / Aktualisiert | 04.02.2017 / 19.02.2017 |
| Lizenzierung | Keine Angabe |
| Weblink |
https://card2brain.ch/box/20170204_cv_chapter_3_segmentation
|
| Einbinden |
<iframe src="https://card2brain.ch/box/20170204_cv_chapter_3_segmentation/embed" width="780" height="150" scrolling="no" frameborder="0"></iframe>
|
What is the motivation of segmentation? [4]
1. Image regions
2. Video frames into shots
3. Figure-ground
4. Object-level
What are the basic questions of segmentation? [2]
1. What things should be grouped?
2. What cues indicate groups?
What are the characteristics of the Gestalt school? [3]
1. “Grouping key to visual perception”
2. Elements of collection can have properties resulting from relations
3. “Whole is greater than sum of its parts”
What are the Gestalt factors? [8]
1. Not grouped // . . . .
2. Proximity // .. .. .. ..
3. Similarity// ***..***
4. Common fate and region
5. Parallelism // << || >>
6. Symmetry // >< || <>
7. Continuity// Edges
8. Closure // o <>
What are difficulties regarding Gestalt factors? [2]
1. Difficult for algorithms
2. Occlusion covers above factors
What is the basic assumption for image segmentation?
Group of pixel that belong together
What are the characteristics of grouping by pixel intensity? [3]
1. Find representative centers and map pixels to nearest
2. Center minimizing SSD Sum|p-c|²
3. Center → Membership and Membership → Center
What is the definition of K-Means algorithm? [3]
1. Randomly initialize k cluster center
2. Determine points for centers
3. If center is false for points update and repeat
