lec02_edge - 9/8/2009 CS6670:ComputerVision NoahSnavely...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
9/8/2009 1 Lecture 2: Edge detection and resampling CS6670: Computer Vision Noah Snavely From Sandlot Science Administrivia New room starting Thursday: HLS B11 Administrivia Assignment 1 (feature detection and matching) will be out Thursday Turning via CMS: https://cms.csuglab.cornell.edu/ Mailing list: please let me know if you aren’t on it Reading Szeliski: 3.4.1, 3.4.2 Last time: Cross correlation This is called a cross correlation operation: Let be the image, be the kernel (of size 2k+1 x 2k+1), and be the output image Last time: Convolution Same as cross correlation, except that the kernel is “flipped” (horizontally and vertically) This is called a convolution operation:
Background image of page 1

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

View Full DocumentRight Arrow Icon
9/8/2009 2 Linear filters: examples 0 0 0 0 1 0 0 0 0 Original Identical image Source: D. Lowe * = Linear filters: examples 0 0 0 0 0 1 0 0 0 Original Shifted left By 1 pixel Source: D. Lowe * = Linear filters: examples Original 1 1 1 1 1 1 1 1 1 Blur (with a mean filter) Source: D. Lowe * = Linear filters: examples Original 1 1 1 1 1 1 1 1 1 0 0 0 0 2 0 0 0 0 - Sharpening filter (accentuates edges) Source: D. Lowe = * Image noise http://theory.uchicago.edu/~ejm/pix/20d/tests/noise/index.html Original image Gaussian noise Salt and pepper noise (each pixel has some chance of being switched to zero or one) Gaussian noise = 1 pixel = 2 pixels = 5 pixels Smoothing with larger standard deviations suppresses noise, but also blurs the image
Background image of page 2
9/8/2009 3 Salt & pepper noise – Gaussian blur = 1 pixel = 2 pixels = 5 pixels What’s wrong with the results? p = 10% Alternative idea: Median filtering •A median filter operates over a window by selecting the median intensity in the window •I s median filtering linear? Source: K. Grauman Median filter •Wha t advantage does median filtering have over Gaussian filtering? Source: K. Grauman Salt & pepper noise–median filtering = 1 pixel = 2 pixels = 5 pixels 3x3 window 5x5 window 7x7 window p = 10% Questions? Edge detection Convert a 2D image into a set of curves Extracts salient features of the scene More compact than pixels
Background image of page 3

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

View Full DocumentRight Arrow Icon
9/8/2009 4 Origin of Edges Edges are caused by a variety of factors depth discontinuity surface color discontinuity illumination discontinuity surface normal discontinuity Characterizing edges •An edge is a place of rapid change in the
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 09/27/2010 for the course CS 667 at Cornell University (Engineering School).

Page1 / 11

lec02_edge - 9/8/2009 CS6670:ComputerVision NoahSnavely...

This preview shows document pages 1 - 5. Sign up to view the full document.

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