CSE527-l4

CSE527-l4 - A biref anlaogy wtih txet Waht mttares is waht...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
1 A biref anlaogy wtih txet Waht mttares is waht hpapens on wrod baounrdies Mocpera iwht htsi sesm 1 Primal Sketch Early vision: invariants, moments, pattern recognition David Marr, late’70s Inspiration from biological vision Image representation in terms of `sketch’ Julesz, `Textons, the fundamental Elements of visual perception’ Sketch components Edges Ridges Blobs Junctions 2
Background image of page 1

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

View Full Document Right Arrow Icon
2 Feature Extraction Features: local meaningful detectable Points Edges Step edges Line edges Contours Closed contours are boundaries Regions Goals for low-level image representation Compact 000000011111100000111111111000 = -6- 01 -3- 10 -4- 01 -7- 10 Generic Same for all tasks, objects, images considered Sufficient No need to look back into the image 4
Background image of page 2
3 Purpose Extract compact, generic, representation of image that carries sufficient information for higher-level processing tasks Essentially what area V1 does in our visual cortex. http://www.usc.edu/programs/vpl/private/photos/research/retinal_circuits/ figure_2.jpg 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 3

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

View Full Document Right Arrow Icon
4 Normalized correlation Think of filters of a dot product now measure the angle i.e normalised correlation output is filter output, divided by root sum of squares of values over which filter lies Tricks: ensure that filter has a zero response to a constant region (helps reduce response to irrelevant background) subtract image average when computing the normalizing constant (i.e. subtract the image mean in the neighbourhood) absolute value deals with contrast reversal Positive responses Zero mean image, -1:1 scale Zero mean image, -max:max scal
Background image of page 4
5 Positive responses Zero mean image, -1:1 scale Zero mean image, -max:max scal Figure from “Computer Vision for Interactive Computer Graphics,” W.Freeman et al, IEEE Computer Graphics and Applications, 1998 copyright 1998, IEEE
Background image of page 5

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

View Full Document Right Arrow Icon
6 Edge Detection Schemes The basic approach to edge detection is to compute “spatial derivatives” of the intensity image The act of taking spatial derivatives is usually approximated by convolution Gradients and edges Points of sharp change in an image are interesting: change in reflectance change in object change in illumination noise Sometimes called edge points General strategy determine image gradient now mark points where gradient magnitude is particularly large wrt neighbours (ideally, curves of such points).
Background image of page 6
7 Finding Edges Consider a 1D signal: I(x) Obvious strategy: look for maxima/minima in
Background image of page 7

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

View Full Document Right Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 33

CSE527-l4 - A biref anlaogy wtih txet Waht mttares is waht...

This preview shows document pages 1 - 8. Sign up to view the full document.

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