{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

cs685-perception-2

cs685-perception-2 - ICRA 2003 Tutorial 1 Image Brightness...

Info icon This preview shows pages 1–12. Sign up to view the full content.

View Full Document Right Arrow Icon
10/15/09 1 1 ICRA 2003 Tutorial Image Brightness values I(x,y)
Image of page 1

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

View Full Document Right Arrow Icon
10/15/09 2 Local, meaningful, detectable parts of the image. Edge detection Line detection Corner detection Motivation Information content high Invariant to change of view point, illumination Reduces computational burden Uniqueness Can be tuned to a task at hand Given a noisy image How do we reduce noise ? How do we find useful features ? Today: Filtering Point-wise operations Edge detection
Image of page 2
10/15/09 3 1D signal and its sampled version f = { f(1), f(2), f(3), …, f(n)} f = {0, 1, 2, 3, 4, 5, 5, 6, 10 } The output of the linear filtering (system) is related to the input via convolution Convolution sum: Notation for convolution: filter h f g f – input signal (image), h – filter, g-output signal (image) Convolution general concept behind linear filtering operations Linear Filters – one means of processing 1D signals Notice weird order of indices: it’s a result of the derivation expressing any shift-invariant linear operator as a convolution.
Image of page 3

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

View Full Document Right Arrow Icon
10/15/09 4 Averaging filter Box filter Averaging filter center pixel weighted more and 0 everywhere else Ex. cont. Original image Smoothed image
Image of page 4
10/15/09 5 CS223b, Jana Kosecka
Image of page 5

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

View Full Document Right Arrow Icon
10/15/09 6
Image of page 6
10/15/09 7 The bigger the mask, more neighbors contribute. smaller noise variance of the output. bigger noise spread. more blurring. more expensive to compute. Signal frequencies shared with noise are lost, resulting in blurring. Impulsive noise is diffused but not removed. The secondary lobes of the sinc let noise into the filtered image (frequency domain interpretation) It spreads the noise, resulting in blurring. Impulsive noise is diffused but not removed.
Image of page 7

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

View Full Document Right Arrow Icon
10/15/09 8 Computer Vision - A Modern Approach Set: Linear Filters Slides by D.A. Forsyth A particular case of averaging The coefficients are samples of a 1D Gaussian. Gives more weight at the central pixel and less weights to the neighbors. The further away the neighbors, the smaller the weight. Sample from the continuous Gaussian
Image of page 8
10/15/09 9 Computer Vision - A Modern Approach Set: Linear Filters Slides by D.A. Forsyth The std. dev of the Gaussian σ determines the amount of smoothing. The samples should adequately represent a Gaussian For a 98.76% of the area, we need m = 5 σ 5.(1/ σ ) 2 π σ 0.796, m 5 g[x] = [0.136, 0.6065, 1.00, 0.606, 0.136] 5-tap filter
Image of page 9

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

View Full Document Right Arrow Icon
10/15/09 10 Convolution with a 2D Gaussian filter Gaussian filter is separable, convolution can be accomplished as two 1-D convolutions The bigger the mask, more neighbors contribute. smaller noise variance of the output. bigger noise spread. more blurring. more expensive to compute.
Image of page 10
10/15/09 11 Signal frequencies shared with noise are lost, resulting in blurring.
Image of page 11

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

View Full Document Right Arrow Icon
Image of page 12
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern