Lecture 10 Flashcards
1
Q
Object classification/recognition
A
automatic labelling of objects based on visual characteristics
2
Q
Feature
A
those components of an image that contain useful information
3
Q
how to find good features:
A
- have some degree of invariance (if things change in the image, the feature representation remain the same)
- are discriminative (object from different categories have different features
- are consistent (objects from the same category have similar feature)
4
Q
What features can be used for Feature detection
A
color histograms
corners
SIFTs
5
Q
SIFT descriptors
A
take a window 16x16 around the key point of interest compute the orientation of gradient at each pixel
6
Q
Application of SIFT
A
Matching key components of two images
7
Q
Scale-invariant feature transform (SIFT)
A
Detects point of interest and computing features descriptors for each point