Summary: Projections
- This + 400k other summaries
- A unique study and practice tool
- Never study anything twice again
- Get the grades you hope for
- 100% sure, 100% understanding
Read the summary and the most important questions on Projections
-
01 Introduction
This is a preview. There are 3 more flashcards available for chapter 01
Show more cards here -
Why visual search engine?
- Growing data requires more efficient solution- Manual indexing is costly and time-consuming- New technologies are needed to automate processes and to unlock possibilities of big data- Metadata standards are needed -
1 Image Filtering
This is a preview. There are 4 more flashcards available for chapter 1
Show more cards here -
What is an edge (derivative)?
An edge is a place of rapid change in the image intensity function -
What is the computational complexity advantage for a separable filter of size k x k, in terms of number of operations per output pixel?
For a k x k Gaussian filter, 2D convolution requires k^2 operations per pixelBut using the separable filters, we reduce this to 2k operations per pixels (3 from top to bottom and 3 from left to right) -
What is the difference between cross-correlation and convolution?
Flip the filter (a, b, c...) > (i, h, g) -
Why do you use the Gaussian kernel?
To find edges.The image is made smooth so the edges are better to be seen. -
How to filter noise?
1. Let's replace each pixel with an average of all the values in its neighbourhood.2. Apply a gaussian filter.Correlation filtering ( G = H (X) F)Convolution (G = H * F) -
What is f(x, y)?
It gives the intensity at position (x, y) -
What is a color image?
Three functions pasted togetherf(x,y) = [r(x,y) g(x,y) b(x,y) -
What is (vector) quantization?
- The process of clustering features- Building the visual vocabulary -
Name three different types of noise
Salt and pepper noise (white and black pixels)impulse noise (white pixels)Gaussian noise (variations in intensity drawn from a Gaussian normal distribution
- Higher grades + faster learning
- Never study anything twice
- 100% sure, 100% understanding