CS223B-L3-Features

CS223B-L3-Features - Stanford CS223B Computer Vision Winter 2008/09 Lecture 3 Features and Linear Filters Professor Sebastian Thrun CAs Ethan

Info iconThis preview shows pages 1–16. Sign up to view the full content.

View Full Document Right Arrow Icon
Sebastian Thrun CS223B Computer Vision, Winter 08/09 Stanford CS223B Computer Vision, Winter 2008/09 Lecture 3 Features and Linear Filters Professor Sebastian Thrun CAs: Ethan Dreyfuss, Young Min Kim, Alex Teichman
Background image of page 1

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

View Full DocumentRight Arrow Icon
Sebastian Thrun CS223B Computer Vision, Winter 08/09 Today’s Question What is a feature? What is an image filter? How can we find corners? How can we find edges? (How can we find cars in images?)
Background image of page 2
Sebastian Thrun CS223B Computer Vision, Winter 08/09 What is a Feature? Local, meaningful, detectable parts of the image
Background image of page 3

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

View Full DocumentRight Arrow Icon
Sebastian Thrun CS223B Computer Vision, Winter 08/09 Features in Computer Vision What is a feature? Location of sudden change Why use features? Information content high Invariant to change of view point, illumination Reduces computational burden
Background image of page 4
Sebastian Thrun CS223B Computer Vision, Winter 08/09 (One Type of) Computer Vision Computer Vision Algorithm Feature 1 Feature 2 : Feature N Feature 1 Feature 2 : Feature N Image 2 Image 1
Background image of page 5

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

View Full DocumentRight Arrow Icon
Sebastian Thrun CS223B Computer Vision, Winter 08/09 Where Features Are Used Calibration Image Segmentation Correspondence in multiple images (stereo, structure from motion) Object detection, classification
Background image of page 6
Sebastian Thrun CS223B Computer Vision, Winter 08/09 What Makes For Good Features? Invariance View point (scale, orientation, translation) Lighting condition Object deformations Partial occlusion Other Characteristics Fast to compute Uniqueness Sufficiently many Tuned to the task
Background image of page 7

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

View Full DocumentRight Arrow Icon
Sebastian Thrun CS223B Computer Vision, Winter 08/09 Edges in Natural Images Photo credit: Photografr.com
Background image of page 8
Sebastian Thrun CS223B Computer Vision, Winter 08/09 Depth discontinuity Surface orientation discontinuity Illumination discontinuity (e.g., shadow) Specular reflection of other discontinuity Reflectance discontinuity (i.e., change in surface material properties) What Causes an Edge? Photo credit: Photografr.com
Background image of page 9

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

View Full DocumentRight Arrow Icon
Sebastian Thrun CS223B Computer Vision, Winter 08/09 A nicer image? 10 Photo credit: Photografr.com
Background image of page 10
Sebastian Thrun CS223B Computer Vision, Winter 08/09 Quiz: How Can We Find Edges?
Background image of page 11

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

View Full DocumentRight Arrow Icon
Sebastian Thrun CS223B Computer Vision, Winter 08/09 Edge Finding 101 cd ~/Documents/cs223b09/notes/code-examples/opencv/1/ im = imread('bridge.jpg'); imshow(im); figure(2); bw = double(rgb2gray(im)) / 256; imshow(bw); gradkernel = [-1 1]; dx = abs(conv2(bw, gradkernel, 'same')); figure(2); imshow(dx); [dx,dy] = gradient(bw); gradmag = sqrt(dx.^2 + dy.^2); figure(3); imshow(gradmag); colorbar colormap(gray(255)) colormap(default) matlab
Background image of page 12
Sebastian Thrun CS223B Computer Vision, Winter 08/09 Edge Finding 101 Example of a linear Filter
Background image of page 13

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

View Full DocumentRight Arrow Icon
Sebastian Thrun CS223B Computer Vision, Winter 08/09 What is (Linear) Image Filtering? Modify the pixels in an image based on some function of a local neighborhood of the pixels 10 5 3 4 5 1 1 1 7 7 Some (linear) function
Background image of page 14
Sebastian Thrun CS223B Computer Vision, Winter 08/09 Linear Filtering Linear case is simplest and most useful Replace each pixel with a linear combination of its neighbors.
Background image of page 15

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

View Full DocumentRight Arrow Icon
Image of page 16
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/30/2009 for the course CS 223B taught by Professor Thrun,s during the Winter '09 term at Stanford.

Page1 / 58

CS223B-L3-Features - Stanford CS223B Computer Vision Winter 2008/09 Lecture 3 Features and Linear Filters Professor Sebastian Thrun CAs Ethan

This preview shows document pages 1 - 16. Sign up to view the full document.

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