Lecture 9 Flashcards
Space Scale
different resolution of an image
zoom in=high spatial freq
zoom out = low spatial freq
Laplacian Pyramid
taking the difference between the gaussian filters
more edge oriented, due to the second derivative extract the edges of the image
Gaussian Pyramid
repeatedly applying the same filter, resulting in
subsampling (reducing size of the image), results in increassingly blurred images
How can create image pyramid
using blur and subsampling
How do the details vary in terms of scaling and spatial frequencies
zoom in , high in details (high spatial frequencies)
zoom out, low in details (low spatial frequencies)
How the Fourier Magnitude Spectrum vary for the
Gaussian pyramid
Images become more blurred
Less high-frequency information
Magnitude plot “comes towards” center
How the Fourier Magnitude Spectrum vary for the
Laplacian pyramid
Only “activity” in one specific ring
As level goes up, this ring gets closer to centre (DC point)
scale invariance
when zooming in, the same patterns remain
Main difference between Gaussian and Laplacian pyramid
Gaussian: results in a low-pass filtered images
Laplacian: results in a band-pass filtered images