CSE527-l6

CSE527-l6 - Feature Extraction Features local meaningful...

Info iconThis preview shows pages 1–11. Sign up to view the full content.

View Full Document Right Arrow Icon
Feature Extraction • Features: local meaningful detectable – Points – Edges • Step edges • Line edges – Contours • Closed contours are boundaries – Regions
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Filters are templates • Applying a filter at some point can be seen as taking a dot- product between the image and some vector • Filtering the image is a set of dot products • Insight – filters look like the effects they are intended to find – filters find effects they look like
Background image of page 2
Smoothing and Differentiation • Issue: noise – smooth before differentiation – two convolutions to smooth, then differentiate? – actually, no - we can use a derivative of Gaussian filter • because differentiation is convolution, and convolution is associative
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
The scale of the smoothing Flter affects derivative estimates, and also the semantics of the edges recovered. 1 pixel 3 pixels 7 pixels
Background image of page 4
Scaled representations • Big bars (resp. spots, hands, etc.) and little bars are both interesting – Stripes and hairs, say • Inefficient to detect big bars with big filters – And there is superfluous detail in the filter kernel • Alternative: – Apply filters of fixed size to images of different sizes – Typically, a collection of images whose edge length changes by a factor of 2 (or root 2) – This is a pyramid (or Gaussian pyramid) by visual analogy
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
A bar in the big images is a hair on the zebra’s nose; in smaller images, a stripe; in the smallest, the animal’s nose
Background image of page 6
Aliasing • Can’t shrink an image by taking every second pixel • If we do, characteristic errors appear – In the next few slides – Typically, small phenomena look bigger; fast phenomena can look slower – Common phenomenon • Wagon wheels rolling the wrong way in movies • Checkerboards misrepresented in ray tracing • Striped shirts look funny on color television
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Resample the checkerboard by taking one sample at each circle. In the case of the top left board, new representation is reasonable. Top right also yields a reasonable representation. Bottom left is all black (dubious) and bottom right has checks that are too big .
Background image of page 8
Constructing a pyramid by taking every second pixel leads to layers that badly misrepresent the top layer
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Open questions • What causes the tendency of differentiation to emphasize noise? • In what precise respects are discrete
Background image of page 10
Image of page 11
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/06/2010 for the course CSE 527 taught by Professor Ab during the Fall '09 term at Cornell.

Page1 / 57

CSE527-l6 - Feature Extraction Features local meaningful...

This preview shows document pages 1 - 11. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online