lec12

lec12 - Convolution R= K*I Filtering and Edge Detection...

This preview shows pages 1–4. Sign up to view the full content.

1 CS252A, Fall 2010 Computer Vision I Filtering and Edge Detection Computer Vision I CSE252A Lecture 12 CS252A, Fall 2010 Computer Vision I Image (I) Kernel (K) * Note: Typically Kernel is relatively small in vision applications. -2 1 1 2 -1 -1 Convolution: R= K*I CS252A, Fall 2010 Computer Vision I Convolution: R= K*I I R Kernel size is m+1 by m+1 m=2 CS252A, Fall 2010 Computer Vision I 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 CS252A, Fall 2010 Computer Vision I Properties of convolution Let f,g,h be images and * denote convolution • Commutative: f*g=g*f • Associative: f*(g*h)=(f*g)*h • Linear: for scalars a & b and images f,g,h (af+bg)*h=a(f*h)+b(g*h) • Differentiation rule CS252A, Fall 2010 Computer Vision I Filtering to reduce noise • Noise is what we’re not interested in. – We’ll discuss simple, low-level noise today: Light fluctuations; Sensor noise; Quantization effects; Finite precision – Not complex: shadows; extraneous objects. • A pixel’s neighborhood contains information about its intensity. • Averaging noise reduces its effect.

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

View Full Document
2 CS252A, Fall 2010 Computer Vision I Additive noise • I = S + N. Noise doesn’t depend on signal. • We’ll consider: CS252A, Fall 2010 Computer Vision I Smoothing with a Gaussian • Notice “ringing” – apparently, a grid is superimposed • Smoothing with an average actually doesn’t compare at all well with a defocussed lens – what does a point of light produce? • A Gaussian gives a good model of a fuzzy blob CS252A, Fall 2010 Computer Vision I Smoothing by Averaging Kernel: CS252A, Fall 2010 Computer Vision I An Isotropic Gaussian • The picture shows a smoothing kernel proportional to (which is a reasonable model of a circularly symmetric fuzzy blob) CS252A, Fall 2010 Computer Vision I Smoothing with a Gaussian Kernel: CS252A, Fall 2010 Computer Vision I The effects of smoothing Each row shows smoothing with gaussians of different width; each column shows different realizations of an image of gaussian noise.
3 CS252A, Fall 2010

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 12/08/2010 for the course CSE 252a taught by Professor Staff during the Fall '08 term at UCSD.

Page1 / 9

lec12 - Convolution R= K*I Filtering and Edge Detection...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online