Bag of Words
4 important questions on Bag of Words
Nearest Neighbour Search algorithm:
- Compute local features in each image independently
- "Label" each feature by a descriptor vector based on its intensity
- Finding corresponding features is transformed to finding nearest neighbour vectors
- Rank matched images by number of corresponding regions
What is Bag of Words?
Learning the visual vocabulary algorithm:
- Regular grid
- Interest points (SIFT)
- Create cluster
- Find the mean cluster
- Higher grades + faster learning
- Never study anything twice
- 100% sure, 100% understanding
What are K-means alternatives?
- Hierarchical clustering
- Spectral clustering
- Vocabulary trees
The question on the page originate from the summary of the following study material:
- A unique study and practice tool
- Never study anything twice again
- Get the grades you hope for
- 100% sure, 100% understanding